backend/index.yaml
Rama master · réplica de lectura del repositorio original.
# Backend gallery: a GENERATED copy of the backend library,
# gallery/backends/index.yaml. The library is the source of truth; edit it, not
# this file. This file is written by scripts/backends/cmd/backendcatalog and
# stays only so releases before the cutover keep working. CI fails when it
# differs from the generated copy:
# go run ./scripts/backends/cmd/backendcatalog --library gallery/backends/index.yaml --out backend/index.yaml
- name: llama-cpp
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
- name: ik-llama-cpp
alias: ik-llama-cpp
license: mit
description: |
Fork of llama.cpp optimized for CPU performance by ikawrakow
urls:
- https://github.com/ikawrakow/ik_llama.cpp
tags:
- text-to-text
- LLM
- CPU
capabilities:
default: cpu-ik-llama-cpp
- name: turboquant
alias: turboquant
license: mit
description: |
Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme.
Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama.
urls:
- https://github.com/TheTom/llama-cpp-turboquant
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- turboquant
- kv-cache
capabilities:
amd: rocm-turboquant
default: cpu-turboquant
intel: intel-sycl-f16-turboquant
nvidia: cuda12-turboquant
nvidia-cuda-12: cuda12-turboquant
nvidia-cuda-13: cuda13-turboquant
nvidia-l4t: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant
vulkan: vulkan-turboquant
- name: bonsai
alias: bonsai
license: apache-2.0
description: |
Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit)
weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses
the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives
these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp
backend.
urls:
- https://github.com/PrismML-Eng/llama.cpp
- https://huggingface.co/prism-ml
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- bonsai
- 1-bit
- ternary
capabilities:
amd: rocm-bonsai
default: cpu-bonsai
intel: intel-sycl-f16-bonsai
nvidia: cuda12-bonsai
nvidia-cuda-12: cuda12-bonsai
nvidia-cuda-13: cuda13-bonsai
nvidia-l4t: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai
vulkan: vulkan-bonsai
- name: ds4
alias: ds4
license: mit
description: |
antirez/ds4 - DeepSeek V4 Flash inference engine. Single-model,
optimized for Metal (Darwin) and CUDA (Linux). Requires the GGUFs
published at huggingface.co/antirez/deepseek-v4-gguf.
urls:
- https://github.com/antirez/ds4
tags:
- text-to-text
- LLM
- CPU
- CUDA
- Metal
capabilities:
default: cpu-ds4
metal: metal-ds4
metal-darwin-arm64: metal-ds4
nvidia: cuda13-ds4
nvidia-cuda-13: cuda13-ds4
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ds4
- name: audio-cpp
alias: audio-cpp
license: apache-2.0
description: |
0xShug0/audio.cpp - a ggml audio inference framework covering text to
speech, voice cloning, transcription, forced alignment, voice activity
detection, speaker diarization, source separation, voice conversion and
music generation, across 30+ model families. Consumes audio.cpp-native
GGUF packages from huggingface.co/audio-cpp/audio.cpp-gguf.
urls:
- https://github.com/0xShug0/audio.cpp
- https://huggingface.co/audio-cpp/audio.cpp-gguf
tags:
- TTS
- text-to-speech
- audio-transcription
- CPU
- CUDA
- HIP
- Metal
capabilities:
amd: rocm-audio-cpp
default: cpu-audio-cpp
metal: metal-audio-cpp
metal-darwin-arm64: metal-audio-cpp
nvidia: cuda12-audio-cpp
nvidia-cuda-12: cuda12-audio-cpp
nvidia-cuda-13: cuda13-audio-cpp
- name: whisper
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
- name: vllm-cpp
alias: vllm-cpp
license: apache-2.0
description: |
ALPHA development builds. Try it, but llama-cpp stays the recommendation for
production use.
vllm.cpp is an Apache-2.0 C++20 inference engine maintained by the LocalAI team,
developed in its own repository and usable without LocalAI. It began as a port of
vLLM and keeps vLLM as its reference implementation, checking output against it and
benchmarking against it, while growing a featureset of its own. It implements vLLM's
V1 architecture (paged KV cache, continuous batching, prefix caching, scheduler,
sampler) on a portable tensor runtime with no Python, PyTorch or ggml at inference
time. It loads GGUF as well as Hugging Face safetensors, supports structured output
(JSON schema / regex / choice / GBNF grammar) enforced in-engine, ships speculative
decoding and KV offload, and runs on CPU, NVIDIA CUDA (Blackwell-family), Apple
Metal and Vulkan.
The project is expected to be renamed as it diverges further from vLLM; the new
name is still to be decided.
urls:
- https://github.com/mudler/vllm.cpp
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- metal
capabilities:
default: cpu-vllm-cpp
metal: metal-vllm-cpp
nvidia: cuda13-vllm-cpp
nvidia-cuda-13: cuda13-vllm-cpp
nvidia-l4t: nvidia-l4t-arm64-vllm-cpp
nvidia-l4t-cuda-13: nvidia-l4t-arm64-vllm-cpp
vulkan: vulkan-vllm-cpp
- name: vllm-cpp-development
alias: vllm-cpp
license: apache-2.0
description: |
ALPHA development builds. Try it, but llama-cpp stays the recommendation for
production use.
vllm.cpp is an Apache-2.0 C++20 inference engine maintained by the LocalAI team,
developed in its own repository and usable without LocalAI. It began as a port of
vLLM and keeps vLLM as its reference implementation, checking output against it and
benchmarking against it, while growing a featureset of its own. It implements vLLM's
V1 architecture (paged KV cache, continuous batching, prefix caching, scheduler,
sampler) on a portable tensor runtime with no Python, PyTorch or ggml at inference
time. It loads GGUF as well as Hugging Face safetensors, supports structured output
(JSON schema / regex / choice / GBNF grammar) enforced in-engine, ships speculative
decoding and KV offload, and runs on CPU, NVIDIA CUDA (Blackwell-family), Apple
Metal and Vulkan.
The project is expected to be renamed as it diverges further from vLLM; the new
name is still to be decided.
urls:
- https://github.com/mudler/vllm.cpp
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- metal
capabilities:
default: cpu-vllm-cpp-development
metal: metal-vllm-cpp-development
nvidia: cuda13-vllm-cpp-development
nvidia-cuda-13: cuda13-vllm-cpp-development
nvidia-l4t: nvidia-l4t-arm64-vllm-cpp-development
nvidia-l4t-cuda-13: nvidia-l4t-arm64-vllm-cpp-development
vulkan: vulkan-vllm-cpp-development
- name: crispasr
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
- name: parakeet-cpp
alias: parakeet-cpp
license: mit
icon: https://avatars.githubusercontent.com/u/95302084
description: |
parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models.
It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription,
and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets.
urls:
- https://github.com/mudler/parakeet.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-parakeet-cpp
default: cpu-parakeet-cpp
intel: intel-sycl-f16-parakeet-cpp
metal: metal-parakeet-cpp
nvidia: cuda12-parakeet-cpp
nvidia-cuda-12: cuda12-parakeet-cpp
nvidia-cuda-13: cuda13-parakeet-cpp
nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp
vulkan: vulkan-parakeet-cpp
- name: nemo-speech-cpp
alias: nemo-speech-cpp
license: apache-2.0
icon: https://avatars.githubusercontent.com/u/1728152?s=200&v=4
description: |
NVIDIA NeMo-Speech.cpp, a C++/ggml runtime for NVIDIA Nemotron Speech models.
One backend serves four model families, selected automatically from the GGUF
general.architecture key: automatic speech recognition (offline, cache-aware
streaming and live transcription, with optional Silero VAD, punctuation,
inverse text normalization and Sortformer speaker diarization attached),
standalone Sortformer diarization, MagpieTTS text-to-speech over NanoCodec,
and Riva-Translate text translation. Runs on CPU, NVIDIA CUDA, Vulkan,
NVIDIA Jetson (L4T) and Apple Metal.
urls:
- https://github.com/NVIDIA/NeMo-Speech.cpp
tags:
- audio-transcription
- text-to-speech
- diarization
- text-to-text
- CPU
- GPU
- CUDA
- Metal
capabilities:
default: cpu-nemo-speech-cpp
metal: metal-nemo-speech-cpp
nvidia: cuda12-nemo-speech-cpp
nvidia-cuda-12: cuda12-nemo-speech-cpp
nvidia-cuda-13: cuda13-nemo-speech-cpp
nvidia-l4t: nvidia-l4t-arm64-nemo-speech-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-nemo-speech-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-nemo-speech-cpp
vulkan: vulkan-nemo-speech-cpp
- name: moss-transcribe-cpp
alias: moss-transcribe-cpp
license: mit
icon: https://avatars.githubusercontent.com/u/95302084
description: |
moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model.
It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled,
time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets.
urls:
- https://github.com/localai-org/moss-transcribe.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-moss-transcribe-cpp
default: cpu-moss-transcribe-cpp
intel: intel-sycl-f16-moss-transcribe-cpp
metal: metal-moss-transcribe-cpp
nvidia: cuda12-moss-transcribe-cpp
nvidia-cuda-12: cuda12-moss-transcribe-cpp
nvidia-cuda-13: cuda13-moss-transcribe-cpp
nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp
vulkan: vulkan-moss-transcribe-cpp
- name: ced
alias: ced
license: mit
icon: https://avatars.githubusercontent.com/u/95302084
description: |
CED sound-event classification / audio tagging (527-class AudioSet).
ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet
taxonomy, exposed through the SoundDetection gRPC rpc and the
/v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA,
AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets.
urls:
- https://github.com/localai-org/ced.cpp
tags:
- audio-classification
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-ced
default: cpu-ced
intel: intel-sycl-f16-ced
metal: metal-ced
nvidia: cuda12-ced
nvidia-cuda-12: cuda12-ced
nvidia-cuda-13: cuda13-ced
nvidia-l4t: nvidia-l4t-arm64-ced
nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced
vulkan: vulkan-ced
- name: voice-detect
alias: voice-detect
license: mit
icon: https://avatars.githubusercontent.com/u/95302084
description: |
voice-detect speaker recognition and voice analysis.
voice-detect.cpp is a C++/ggml engine that produces L2-normalised
speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker
ERes2Net, CAM++) for voice verification and 1:N identification, plus
a wav2vec2 age / gender / emotion analysis head. It replaces the
Python speaker-recognition backend and is exposed through the Voice*
gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA
CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets.
urls:
- https://github.com/localai-org/voice-detect.cpp
tags:
- voice-recognition
- speaker-verification
- speaker-embedding
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-voice-detect
default: cpu-voice-detect
intel: intel-sycl-f16-voice-detect
metal: metal-voice-detect
nvidia: cuda12-voice-detect
nvidia-cuda-12: cuda12-voice-detect
nvidia-cuda-13: cuda13-voice-detect
nvidia-l4t: nvidia-l4t-arm64-voice-detect
nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect
vulkan: vulkan-voice-detect
- name: face-detect
alias: face-detect
license: mit
icon: https://avatars.githubusercontent.com/u/95302084
description: |
face-detect face detection, embedding, verification and analysis.
face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face
detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face
embeddings for verification and 1:N identification, plus a landmark /
age / gender analysis head. It replaces the Python insightface backend
and is exposed through the Embedding, Detect and Face* gRPC rpcs and
the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD
ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets.
urls:
- https://github.com/mudler/face-detect.cpp
tags:
- face-recognition
- face-verification
- face-embedding
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-face-detect
default: cpu-face-detect
intel: intel-sycl-f16-face-detect
metal: metal-face-detect
nvidia: cuda12-face-detect
nvidia-cuda-12: cuda12-face-detect
nvidia-cuda-13: cuda13-face-detect
nvidia-l4t: nvidia-l4t-arm64-face-detect
nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect
vulkan: vulkan-face-detect
- name: voxtral
alias: voxtral
license: mit
description: |
Voxtral Realtime 4B Pure C speech-to-text inference engine
urls:
- https://github.com/mudler/voxtral.c
tags:
- audio-transcription
- CPU
- Metal
capabilities:
default: cpu-voxtral
metal-darwin-arm64: metal-voxtral
- name: stablediffusion-ggml
alias: stablediffusion-ggml
license: mit
icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png
description: |
Stable Diffusion and Flux in pure C/C++
urls:
- https://github.com/leejet/stable-diffusion.cpp
tags:
- image-generation
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-stablediffusion-ggml
default: cpu-stablediffusion-ggml
intel: intel-sycl-f16-stablediffusion-ggml
metal: metal-stablediffusion-ggml
nvidia: cuda12-stablediffusion-ggml
nvidia-cuda-12: cuda12-stablediffusion-ggml
nvidia-cuda-13: cuda13-stablediffusion-ggml
nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml
nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml
vulkan: vulkan-stablediffusion-ggml
- name: kimodocpp
alias: kimodocpp
license: apache-2.0
description: |
kimodo.cpp text-to-motion: animated skeleton GLB on CPU and Vulkan.
Apple Silicon uses the CPU runtime.
urls:
- https://github.com/localai-org/kimodo.cpp
tags:
- 3d-animation
- text-to-motion
- CPU
- Vulkan
capabilities:
amd: vulkan-kimodocpp
default: cpu-kimodocpp
intel: vulkan-kimodocpp
metal: cpu-darwin-arm64-kimodocpp
nvidia: vulkan-kimodocpp
nvidia-cuda-12: vulkan-kimodocpp
nvidia-cuda-13: vulkan-kimodocpp
vulkan: vulkan-kimodocpp
- name: gemxcpp
alias: gemxcpp
license: apache-2.0
description: |
gem-x.cpp live human motion: SOMA and SMPL pose streams on CPU and Vulkan.
Apple Silicon uses the CPU runtime.
urls:
- https://github.com/localai-org/gem-x.cpp
tags:
- motion
- pose-estimation
- CPU
- Vulkan
capabilities:
amd: vulkan-gemxcpp
default: cpu-gemxcpp
intel: vulkan-gemxcpp
metal: cpu-darwin-arm64-gemxcpp
nvidia: vulkan-gemxcpp
nvidia-cuda-12: vulkan-gemxcpp
nvidia-cuda-13: vulkan-gemxcpp
vulkan: vulkan-gemxcpp
- name: trellis2cpp
alias: trellis2cpp
license: mit
description: |
TRELLIS.2 image-to-3D generation (GLB meshes with PBR textures) in C++/ggml
urls:
- https://github.com/localai-org/trellis2cpp
- https://github.com/microsoft/TRELLIS.2
tags:
- image-to-3d
- 3d-generation
- CPU
- GPU
- CUDA
- Metal
capabilities:
default: cpu-trellis2cpp
metal: metal-trellis2cpp
nvidia: cuda12-trellis2cpp
nvidia-cuda-12: cuda12-trellis2cpp
nvidia-cuda-13: cuda13-trellis2cpp
nvidia-l4t: nvidia-l4t-arm64-trellis2cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-trellis2cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-trellis2cpp
vulkan: vulkan-trellis2cpp
- name: rfdetr
alias: rfdetr
license: apache-2.0
icon: https://avatars.githubusercontent.com/u/53104118?s=200&v=4
description: |
RF-DETR is a real-time, transformer-based object detection model architecture developed by Roboflow and released under the Apache 2.0 license.
RF-DETR is the first real-time model to exceed 60 AP on the Microsoft COCO benchmark alongside competitive performance at base sizes. It also achieves state-of-the-art performance on RF100-VL, an object detection benchmark that measures model domain adaptability to real world problems. RF-DETR is fastest and most accurate for its size when compared current real-time objection models.
RF-DETR is small enough to run on the edge using Inference, making it an ideal model for deployments that need both strong accuracy and real-time performance.
urls:
- https://github.com/roboflow/rf-detr
tags:
- object-detection
- rfdetr
- gpu
- cpu
capabilities:
default: cpu-rfdetr
intel: intel-rfdetr
metal: metal-rfdetr
nvidia: cuda12-rfdetr
nvidia-cuda-12: cuda12-rfdetr
nvidia-cuda-13: cuda13-rfdetr
nvidia-l4t: nvidia-l4t-arm64-rfdetr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr
- name: insightface
alias: insightface
license: mixed
description: |
Face recognition backend powered by `insightface` (ONNX Runtime).
Provides face verification (/v1/face/verify), face analysis
(/v1/face/analyze), face embedding (/v1/embeddings), face
detection (/v1/detection), and 1:N identification
(/v1/face/{register,identify,forget}).
Ships two engines in a single image: one that drives the insightface
model packs (buffalo_l/s/m/sc, antelopev2 — non-commercial research
use only) and one that drives OpenCV Zoo's YuNet + SFace pair
(Apache 2.0 — commercial-safe). Select via `options: ["engine:..."]`
in your model YAML, or install one of the ready-made model-gallery
entries under the `insightface-*` prefix.
The backend image contains only code and Python deps; all model
weights are managed by LocalAI's gallery download mechanism.
urls:
- https://github.com/deepinsight/insightface
- https://github.com/opencv/opencv_zoo
tags:
- face-recognition
- face-verification
- face-embedding
- gpu
- cpu
capabilities:
default: cpu-insightface
nvidia: cuda12-insightface
nvidia-cuda-12: cuda12-insightface
- name: sam3-cpp
alias: sam3-cpp
license: mit
description: |
Segment Anything Model (SAM 3/2/EdgeTAM) in C/C++ using GGML.
Supports text-prompted and point/box-prompted image segmentation.
urls:
- https://github.com/PABannier/sam3.cpp
tags:
- image-segmentation
- object-detection
- sam3
- gpu
- cpu
capabilities:
default: cpu-sam3-cpp
intel: intel-sycl-f32-sam3-cpp
metal: metal-sam3-cpp
nvidia: cuda12-sam3-cpp
nvidia-cuda-12: cuda12-sam3-cpp
nvidia-cuda-13: cuda13-sam3-cpp
nvidia-l4t: nvidia-l4t-arm64-sam3-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-sam3-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sam3-cpp
vulkan: vulkan-sam3-cpp
- name: rfdetr-cpp
alias: rfdetr-cpp
license: apache-2.0
description: |
Native RF-DETR object detection and instance segmentation in C/C++
using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-*
family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium)
and returns bounding boxes, class labels, confidence scores, and
(for segmentation variants) PNG-encoded per-detection masks.
urls:
- https://github.com/localai-org/rf-detr.cpp
tags:
- object-detection
- image-segmentation
- rfdetr
- gpu
- cpu
capabilities:
default: cpu-rfdetr-cpp
intel: intel-sycl-f32-rfdetr-cpp
metal: metal-rfdetr-cpp
nvidia: cuda12-rfdetr-cpp
nvidia-cuda-12: cuda12-rfdetr-cpp
nvidia-cuda-13: cuda13-rfdetr-cpp
nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp
vulkan: vulkan-rfdetr-cpp
- name: locate-anything
alias: locate-anything
license: apache-2.0
description: |
Open-vocabulary object detection and visual grounding (NVIDIA
LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights
and, given an image and a free-form text prompt, returns bounding
boxes, class labels, and confidence scores for the referred objects.
urls:
- https://github.com/mudler/locate-anything.cpp
- https://huggingface.co/nvidia/LocateAnything-3B
tags:
- object-detection
- visual-grounding
- open-vocabulary
- locate-anything
- gpu
- cpu
capabilities:
default: cpu-locate-anything-cpp
intel: intel-sycl-f32-locate-anything-cpp
metal: metal-locate-anything-cpp
nvidia: cuda12-locate-anything-cpp
nvidia-cuda-12: cuda12-locate-anything-cpp
nvidia-cuda-13: cuda13-locate-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp
vulkan: vulkan-locate-anything-cpp
- name: locate-anything-development
alias: locate-anything
license: apache-2.0
description: |
Open-vocabulary object detection and visual grounding (NVIDIA
LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights
and, given an image and a free-form text prompt, returns bounding
boxes, class labels, and confidence scores for the referred objects.
urls:
- https://github.com/mudler/locate-anything.cpp
- https://huggingface.co/nvidia/LocateAnything-3B
tags:
- object-detection
- visual-grounding
- open-vocabulary
- locate-anything
- gpu
- cpu
capabilities:
default: cpu-locate-anything-cpp-development
intel: intel-sycl-f32-locate-anything-cpp-development
metal: metal-locate-anything-cpp-development
nvidia: cuda12-locate-anything-cpp-development
nvidia-cuda-12: cuda12-locate-anything-cpp-development
nvidia-cuda-13: cuda13-locate-anything-cpp-development
nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp-development
nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp-development
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp-development
vulkan: vulkan-locate-anything-cpp-development
- name: cpu-locate-anything-cpp
alias: locate-anything
license: apache-2.0
description: |
Open-vocabulary object detection and visual grounding (NVIDIA
LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights
and, given an image and a free-form text prompt, returns bounding
boxes, class labels, and confidence scores for the referred objects.
urls:
- https://github.com/mudler/locate-anything.cpp
- https://huggingface.co/nvidia/LocateAnything-3B
tags:
- object-detection
- visual-grounding
- open-vocabulary
- locate-anything
- gpu
- cpu
capabilities:
default: cpu-locate-anything-cpp
intel: intel-sycl-f32-locate-anything-cpp
metal: metal-locate-anything-cpp
nvidia: cuda12-locate-anything-cpp
nvidia-cuda-12: cuda12-locate-anything-cpp
nvidia-cuda-13: cuda13-locate-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp
vulkan: vulkan-locate-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-locate-anything-cpp
mirrors:
- localai/localai-backends:latest-cpu-locate-anything-cpp
- name: cpu-locate-anything-cpp-development
alias: locate-anything
license: apache-2.0
description: |
Open-vocabulary object detection and visual grounding (NVIDIA
LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights
and, given an image and a free-form text prompt, returns bounding
boxes, class labels, and confidence scores for the referred objects.
urls:
- https://github.com/mudler/locate-anything.cpp
- https://huggingface.co/nvidia/LocateAnything-3B
tags:
- object-detection
- visual-grounding
- open-vocabulary
- locate-anything
- gpu
- cpu
capabilities:
default: cpu-locate-anything-cpp
intel: intel-sycl-f32-locate-anything-cpp
metal: metal-locate-anything-cpp
nvidia: cuda12-locate-anything-cpp
nvidia-cuda-12: cuda12-locate-anything-cpp
nvidia-cuda-13: cuda13-locate-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp
vulkan: vulkan-locate-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:master-cpu-locate-anything-cpp
mirrors:
- localai/localai-backends:master-cpu-locate-anything-cpp
- name: metal-locate-anything-cpp
alias: locate-anything
license: apache-2.0
description: |
Open-vocabulary object detection and visual grounding (NVIDIA
LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights
and, given an image and a free-form text prompt, returns bounding
boxes, class labels, and confidence scores for the referred objects.
urls:
- https://github.com/mudler/locate-anything.cpp
- https://huggingface.co/nvidia/LocateAnything-3B
tags:
- object-detection
- visual-grounding
- open-vocabulary
- locate-anything
- gpu
- cpu
capabilities:
default: cpu-locate-anything-cpp
intel: intel-sycl-f32-locate-anything-cpp
metal: metal-locate-anything-cpp
nvidia: cuda12-locate-anything-cpp
nvidia-cuda-12: cuda12-locate-anything-cpp
nvidia-cuda-13: cuda13-locate-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp
vulkan: vulkan-locate-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-locate-anything-cpp
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-locate-anything-cpp
- name: metal-locate-anything-cpp-development
alias: locate-anything
license: apache-2.0
description: |
Open-vocabulary object detection and visual grounding (NVIDIA
LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights
and, given an image and a free-form text prompt, returns bounding
boxes, class labels, and confidence scores for the referred objects.
urls:
- https://github.com/mudler/locate-anything.cpp
- https://huggingface.co/nvidia/LocateAnything-3B
tags:
- object-detection
- visual-grounding
- open-vocabulary
- locate-anything
- gpu
- cpu
capabilities:
default: cpu-locate-anything-cpp
intel: intel-sycl-f32-locate-anything-cpp
metal: metal-locate-anything-cpp
nvidia: cuda12-locate-anything-cpp
nvidia-cuda-12: cuda12-locate-anything-cpp
nvidia-cuda-13: cuda13-locate-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp
vulkan: vulkan-locate-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-locate-anything-cpp
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-locate-anything-cpp
- name: cuda12-locate-anything-cpp
alias: locate-anything
license: apache-2.0
description: |
Open-vocabulary object detection and visual grounding (NVIDIA
LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights
and, given an image and a free-form text prompt, returns bounding
boxes, class labels, and confidence scores for the referred objects.
urls:
- https://github.com/mudler/locate-anything.cpp
- https://huggingface.co/nvidia/LocateAnything-3B
tags:
- object-detection
- visual-grounding
- open-vocabulary
- locate-anything
- gpu
- cpu
capabilities:
default: cpu-locate-anything-cpp
intel: intel-sycl-f32-locate-anything-cpp
metal: metal-locate-anything-cpp
nvidia: cuda12-locate-anything-cpp
nvidia-cuda-12: cuda12-locate-anything-cpp
nvidia-cuda-13: cuda13-locate-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp
vulkan: vulkan-locate-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-locate-anything-cpp
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-12-locate-anything-cpp
- name: cuda12-locate-anything-cpp-development
alias: locate-anything
license: apache-2.0
description: |
Open-vocabulary object detection and visual grounding (NVIDIA
LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights
and, given an image and a free-form text prompt, returns bounding
boxes, class labels, and confidence scores for the referred objects.
urls:
- https://github.com/mudler/locate-anything.cpp
- https://huggingface.co/nvidia/LocateAnything-3B
tags:
- object-detection
- visual-grounding
- open-vocabulary
- locate-anything
- gpu
- cpu
capabilities:
default: cpu-locate-anything-cpp
intel: intel-sycl-f32-locate-anything-cpp
metal: metal-locate-anything-cpp
nvidia: cuda12-locate-anything-cpp
nvidia-cuda-12: cuda12-locate-anything-cpp
nvidia-cuda-13: cuda13-locate-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp
vulkan: vulkan-locate-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-locate-anything-cpp
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-12-locate-anything-cpp
- name: cuda13-locate-anything-cpp
alias: locate-anything
license: apache-2.0
description: |
Open-vocabulary object detection and visual grounding (NVIDIA
LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights
and, given an image and a free-form text prompt, returns bounding
boxes, class labels, and confidence scores for the referred objects.
urls:
- https://github.com/mudler/locate-anything.cpp
- https://huggingface.co/nvidia/LocateAnything-3B
tags:
- object-detection
- visual-grounding
- open-vocabulary
- locate-anything
- gpu
- cpu
capabilities:
default: cpu-locate-anything-cpp
intel: intel-sycl-f32-locate-anything-cpp
metal: metal-locate-anything-cpp
nvidia: cuda12-locate-anything-cpp
nvidia-cuda-12: cuda12-locate-anything-cpp
nvidia-cuda-13: cuda13-locate-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp
vulkan: vulkan-locate-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-locate-anything-cpp
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-13-locate-anything-cpp
- name: cuda13-locate-anything-cpp-development
alias: locate-anything
license: apache-2.0
description: |
Open-vocabulary object detection and visual grounding (NVIDIA
LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights
and, given an image and a free-form text prompt, returns bounding
boxes, class labels, and confidence scores for the referred objects.
urls:
- https://github.com/mudler/locate-anything.cpp
- https://huggingface.co/nvidia/LocateAnything-3B
tags:
- object-detection
- visual-grounding
- open-vocabulary
- locate-anything
- gpu
- cpu
capabilities:
default: cpu-locate-anything-cpp
intel: intel-sycl-f32-locate-anything-cpp
metal: metal-locate-anything-cpp
nvidia: cuda12-locate-anything-cpp
nvidia-cuda-12: cuda12-locate-anything-cpp
nvidia-cuda-13: cuda13-locate-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp
vulkan: vulkan-locate-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-locate-anything-cpp
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-13-locate-anything-cpp
- name: nvidia-l4t-arm64-locate-anything-cpp
alias: locate-anything
license: apache-2.0
description: |
Open-vocabulary object detection and visual grounding (NVIDIA
LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights
and, given an image and a free-form text prompt, returns bounding
boxes, class labels, and confidence scores for the referred objects.
urls:
- https://github.com/mudler/locate-anything.cpp
- https://huggingface.co/nvidia/LocateAnything-3B
tags:
- object-detection
- visual-grounding
- open-vocabulary
- locate-anything
- gpu
- cpu
capabilities:
default: cpu-locate-anything-cpp
intel: intel-sycl-f32-locate-anything-cpp
metal: metal-locate-anything-cpp
nvidia: cuda12-locate-anything-cpp
nvidia-cuda-12: cuda12-locate-anything-cpp
nvidia-cuda-13: cuda13-locate-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp
vulkan: vulkan-locate-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-locate-anything-cpp
mirrors:
- localai/localai-backends:latest-nvidia-l4t-arm64-locate-anything-cpp
- name: nvidia-l4t-arm64-locate-anything-cpp-development
alias: locate-anything
license: apache-2.0
description: |
Open-vocabulary object detection and visual grounding (NVIDIA
LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights
and, given an image and a free-form text prompt, returns bounding
boxes, class labels, and confidence scores for the referred objects.
urls:
- https://github.com/mudler/locate-anything.cpp
- https://huggingface.co/nvidia/LocateAnything-3B
tags:
- object-detection
- visual-grounding
- open-vocabulary
- locate-anything
- gpu
- cpu
capabilities:
default: cpu-locate-anything-cpp
intel: intel-sycl-f32-locate-anything-cpp
metal: metal-locate-anything-cpp
nvidia: cuda12-locate-anything-cpp
nvidia-cuda-12: cuda12-locate-anything-cpp
nvidia-cuda-13: cuda13-locate-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp
vulkan: vulkan-locate-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-locate-anything-cpp
mirrors:
- localai/localai-backends:master-nvidia-l4t-arm64-locate-anything-cpp
- name: cuda13-nvidia-l4t-arm64-locate-anything-cpp
alias: locate-anything
license: apache-2.0
description: |
Open-vocabulary object detection and visual grounding (NVIDIA
LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights
and, given an image and a free-form text prompt, returns bounding
boxes, class labels, and confidence scores for the referred objects.
urls:
- https://github.com/mudler/locate-anything.cpp
- https://huggingface.co/nvidia/LocateAnything-3B
tags:
- object-detection
- visual-grounding
- open-vocabulary
- locate-anything
- gpu
- cpu
capabilities:
default: cpu-locate-anything-cpp
intel: intel-sycl-f32-locate-anything-cpp
metal: metal-locate-anything-cpp
nvidia: cuda12-locate-anything-cpp
nvidia-cuda-12: cuda12-locate-anything-cpp
nvidia-cuda-13: cuda13-locate-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp
vulkan: vulkan-locate-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-locate-anything-cpp
mirrors:
- localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-locate-anything-cpp
- name: cuda13-nvidia-l4t-arm64-locate-anything-cpp-development
alias: locate-anything
license: apache-2.0
description: |
Open-vocabulary object detection and visual grounding (NVIDIA
LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights
and, given an image and a free-form text prompt, returns bounding
boxes, class labels, and confidence scores for the referred objects.
urls:
- https://github.com/mudler/locate-anything.cpp
- https://huggingface.co/nvidia/LocateAnything-3B
tags:
- object-detection
- visual-grounding
- open-vocabulary
- locate-anything
- gpu
- cpu
capabilities:
default: cpu-locate-anything-cpp
intel: intel-sycl-f32-locate-anything-cpp
metal: metal-locate-anything-cpp
nvidia: cuda12-locate-anything-cpp
nvidia-cuda-12: cuda12-locate-anything-cpp
nvidia-cuda-13: cuda13-locate-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp
vulkan: vulkan-locate-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-locate-anything-cpp
mirrors:
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-locate-anything-cpp
- name: intel-sycl-f32-locate-anything-cpp
alias: locate-anything
license: apache-2.0
description: |
Open-vocabulary object detection and visual grounding (NVIDIA
LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights
and, given an image and a free-form text prompt, returns bounding
boxes, class labels, and confidence scores for the referred objects.
urls:
- https://github.com/mudler/locate-anything.cpp
- https://huggingface.co/nvidia/LocateAnything-3B
tags:
- object-detection
- visual-grounding
- open-vocabulary
- locate-anything
- gpu
- cpu
capabilities:
default: cpu-locate-anything-cpp
intel: intel-sycl-f32-locate-anything-cpp
metal: metal-locate-anything-cpp
nvidia: cuda12-locate-anything-cpp
nvidia-cuda-12: cuda12-locate-anything-cpp
nvidia-cuda-13: cuda13-locate-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp
vulkan: vulkan-locate-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-locate-anything-cpp
mirrors:
- localai/localai-backends:latest-gpu-intel-sycl-f32-locate-anything-cpp
- name: intel-sycl-f32-locate-anything-cpp-development
alias: locate-anything
license: apache-2.0
description: |
Open-vocabulary object detection and visual grounding (NVIDIA
LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights
and, given an image and a free-form text prompt, returns bounding
boxes, class labels, and confidence scores for the referred objects.
urls:
- https://github.com/mudler/locate-anything.cpp
- https://huggingface.co/nvidia/LocateAnything-3B
tags:
- object-detection
- visual-grounding
- open-vocabulary
- locate-anything
- gpu
- cpu
capabilities:
default: cpu-locate-anything-cpp
intel: intel-sycl-f32-locate-anything-cpp
metal: metal-locate-anything-cpp
nvidia: cuda12-locate-anything-cpp
nvidia-cuda-12: cuda12-locate-anything-cpp
nvidia-cuda-13: cuda13-locate-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp
vulkan: vulkan-locate-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-locate-anything-cpp
mirrors:
- localai/localai-backends:master-gpu-intel-sycl-f32-locate-anything-cpp
- name: intel-sycl-f16-locate-anything-cpp
alias: locate-anything
license: apache-2.0
description: |
Open-vocabulary object detection and visual grounding (NVIDIA
LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights
and, given an image and a free-form text prompt, returns bounding
boxes, class labels, and confidence scores for the referred objects.
urls:
- https://github.com/mudler/locate-anything.cpp
- https://huggingface.co/nvidia/LocateAnything-3B
tags:
- object-detection
- visual-grounding
- open-vocabulary
- locate-anything
- gpu
- cpu
capabilities:
default: cpu-locate-anything-cpp
intel: intel-sycl-f32-locate-anything-cpp
metal: metal-locate-anything-cpp
nvidia: cuda12-locate-anything-cpp
nvidia-cuda-12: cuda12-locate-anything-cpp
nvidia-cuda-13: cuda13-locate-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp
vulkan: vulkan-locate-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-locate-anything-cpp
mirrors:
- localai/localai-backends:latest-gpu-intel-sycl-f16-locate-anything-cpp
- name: intel-sycl-f16-locate-anything-cpp-development
alias: locate-anything
license: apache-2.0
description: |
Open-vocabulary object detection and visual grounding (NVIDIA
LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights
and, given an image and a free-form text prompt, returns bounding
boxes, class labels, and confidence scores for the referred objects.
urls:
- https://github.com/mudler/locate-anything.cpp
- https://huggingface.co/nvidia/LocateAnything-3B
tags:
- object-detection
- visual-grounding
- open-vocabulary
- locate-anything
- gpu
- cpu
capabilities:
default: cpu-locate-anything-cpp
intel: intel-sycl-f32-locate-anything-cpp
metal: metal-locate-anything-cpp
nvidia: cuda12-locate-anything-cpp
nvidia-cuda-12: cuda12-locate-anything-cpp
nvidia-cuda-13: cuda13-locate-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp
vulkan: vulkan-locate-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-locate-anything-cpp
mirrors:
- localai/localai-backends:master-gpu-intel-sycl-f16-locate-anything-cpp
- name: vulkan-locate-anything-cpp
alias: locate-anything
license: apache-2.0
description: |
Open-vocabulary object detection and visual grounding (NVIDIA
LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights
and, given an image and a free-form text prompt, returns bounding
boxes, class labels, and confidence scores for the referred objects.
urls:
- https://github.com/mudler/locate-anything.cpp
- https://huggingface.co/nvidia/LocateAnything-3B
tags:
- object-detection
- visual-grounding
- open-vocabulary
- locate-anything
- gpu
- cpu
capabilities:
default: cpu-locate-anything-cpp
intel: intel-sycl-f32-locate-anything-cpp
metal: metal-locate-anything-cpp
nvidia: cuda12-locate-anything-cpp
nvidia-cuda-12: cuda12-locate-anything-cpp
nvidia-cuda-13: cuda13-locate-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp
vulkan: vulkan-locate-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-locate-anything-cpp
mirrors:
- localai/localai-backends:latest-gpu-vulkan-locate-anything-cpp
- name: vulkan-locate-anything-cpp-development
alias: locate-anything
license: apache-2.0
description: |
Open-vocabulary object detection and visual grounding (NVIDIA
LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights
and, given an image and a free-form text prompt, returns bounding
boxes, class labels, and confidence scores for the referred objects.
urls:
- https://github.com/mudler/locate-anything.cpp
- https://huggingface.co/nvidia/LocateAnything-3B
tags:
- object-detection
- visual-grounding
- open-vocabulary
- locate-anything
- gpu
- cpu
capabilities:
default: cpu-locate-anything-cpp
intel: intel-sycl-f32-locate-anything-cpp
metal: metal-locate-anything-cpp
nvidia: cuda12-locate-anything-cpp
nvidia-cuda-12: cuda12-locate-anything-cpp
nvidia-cuda-13: cuda13-locate-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp
vulkan: vulkan-locate-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-locate-anything-cpp
mirrors:
- localai/localai-backends:master-gpu-vulkan-locate-anything-cpp
- name: depth-anything
alias: depth-anything
license: apache-2.0
description: |
Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
using GGML. Loads pre-built GGUF weights and, given an image, returns a
dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
(3x3). No Python at inference (purego, cgo-less).
urls:
- https://github.com/mudler/depth-anything.cpp
- https://huggingface.co/depth-anything/Depth-Anything-V3
tags:
- depth-estimation
- camera-pose
- depth-anything
- gpu
- cpu
capabilities:
default: cpu-depth-anything-cpp
intel: intel-sycl-f32-depth-anything-cpp
metal: metal-depth-anything-cpp
nvidia: cuda12-depth-anything-cpp
nvidia-cuda-12: cuda12-depth-anything-cpp
nvidia-cuda-13: cuda13-depth-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp
vulkan: vulkan-depth-anything-cpp
- name: depth-anything-development
alias: depth-anything
license: apache-2.0
description: |
Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
using GGML. Loads pre-built GGUF weights and, given an image, returns a
dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
(3x3). No Python at inference (purego, cgo-less).
urls:
- https://github.com/mudler/depth-anything.cpp
- https://huggingface.co/depth-anything/Depth-Anything-V3
tags:
- depth-estimation
- camera-pose
- depth-anything
- gpu
- cpu
capabilities:
default: cpu-depth-anything-cpp-development
intel: intel-sycl-f32-depth-anything-cpp-development
metal: metal-depth-anything-cpp-development
nvidia: cuda12-depth-anything-cpp-development
nvidia-cuda-12: cuda12-depth-anything-cpp-development
nvidia-cuda-13: cuda13-depth-anything-cpp-development
nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp-development
nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp-development
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp-development
vulkan: vulkan-depth-anything-cpp-development
- name: cpu-depth-anything-cpp
alias: depth-anything
license: apache-2.0
description: |
Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
using GGML. Loads pre-built GGUF weights and, given an image, returns a
dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
(3x3). No Python at inference (purego, cgo-less).
urls:
- https://github.com/mudler/depth-anything.cpp
- https://huggingface.co/depth-anything/Depth-Anything-V3
tags:
- depth-estimation
- camera-pose
- depth-anything
- gpu
- cpu
capabilities:
default: cpu-depth-anything-cpp
intel: intel-sycl-f32-depth-anything-cpp
metal: metal-depth-anything-cpp
nvidia: cuda12-depth-anything-cpp
nvidia-cuda-12: cuda12-depth-anything-cpp
nvidia-cuda-13: cuda13-depth-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp
vulkan: vulkan-depth-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-depth-anything-cpp
mirrors:
- localai/localai-backends:latest-cpu-depth-anything-cpp
- name: cpu-depth-anything-cpp-development
alias: depth-anything
license: apache-2.0
description: |
Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
using GGML. Loads pre-built GGUF weights and, given an image, returns a
dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
(3x3). No Python at inference (purego, cgo-less).
urls:
- https://github.com/mudler/depth-anything.cpp
- https://huggingface.co/depth-anything/Depth-Anything-V3
tags:
- depth-estimation
- camera-pose
- depth-anything
- gpu
- cpu
capabilities:
default: cpu-depth-anything-cpp
intel: intel-sycl-f32-depth-anything-cpp
metal: metal-depth-anything-cpp
nvidia: cuda12-depth-anything-cpp
nvidia-cuda-12: cuda12-depth-anything-cpp
nvidia-cuda-13: cuda13-depth-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp
vulkan: vulkan-depth-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:master-cpu-depth-anything-cpp
mirrors:
- localai/localai-backends:master-cpu-depth-anything-cpp
- name: metal-depth-anything-cpp
alias: depth-anything
license: apache-2.0
description: |
Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
using GGML. Loads pre-built GGUF weights and, given an image, returns a
dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
(3x3). No Python at inference (purego, cgo-less).
urls:
- https://github.com/mudler/depth-anything.cpp
- https://huggingface.co/depth-anything/Depth-Anything-V3
tags:
- depth-estimation
- camera-pose
- depth-anything
- gpu
- cpu
capabilities:
default: cpu-depth-anything-cpp
intel: intel-sycl-f32-depth-anything-cpp
metal: metal-depth-anything-cpp
nvidia: cuda12-depth-anything-cpp
nvidia-cuda-12: cuda12-depth-anything-cpp
nvidia-cuda-13: cuda13-depth-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp
vulkan: vulkan-depth-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-depth-anything-cpp
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-depth-anything-cpp
- name: metal-depth-anything-cpp-development
alias: depth-anything
license: apache-2.0
description: |
Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
using GGML. Loads pre-built GGUF weights and, given an image, returns a
dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
(3x3). No Python at inference (purego, cgo-less).
urls:
- https://github.com/mudler/depth-anything.cpp
- https://huggingface.co/depth-anything/Depth-Anything-V3
tags:
- depth-estimation
- camera-pose
- depth-anything
- gpu
- cpu
capabilities:
default: cpu-depth-anything-cpp
intel: intel-sycl-f32-depth-anything-cpp
metal: metal-depth-anything-cpp
nvidia: cuda12-depth-anything-cpp
nvidia-cuda-12: cuda12-depth-anything-cpp
nvidia-cuda-13: cuda13-depth-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp
vulkan: vulkan-depth-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-depth-anything-cpp
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-depth-anything-cpp
- name: cuda12-depth-anything-cpp
alias: depth-anything
license: apache-2.0
description: |
Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
using GGML. Loads pre-built GGUF weights and, given an image, returns a
dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
(3x3). No Python at inference (purego, cgo-less).
urls:
- https://github.com/mudler/depth-anything.cpp
- https://huggingface.co/depth-anything/Depth-Anything-V3
tags:
- depth-estimation
- camera-pose
- depth-anything
- gpu
- cpu
capabilities:
default: cpu-depth-anything-cpp
intel: intel-sycl-f32-depth-anything-cpp
metal: metal-depth-anything-cpp
nvidia: cuda12-depth-anything-cpp
nvidia-cuda-12: cuda12-depth-anything-cpp
nvidia-cuda-13: cuda13-depth-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp
vulkan: vulkan-depth-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-depth-anything-cpp
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-12-depth-anything-cpp
- name: cuda12-depth-anything-cpp-development
alias: depth-anything
license: apache-2.0
description: |
Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
using GGML. Loads pre-built GGUF weights and, given an image, returns a
dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
(3x3). No Python at inference (purego, cgo-less).
urls:
- https://github.com/mudler/depth-anything.cpp
- https://huggingface.co/depth-anything/Depth-Anything-V3
tags:
- depth-estimation
- camera-pose
- depth-anything
- gpu
- cpu
capabilities:
default: cpu-depth-anything-cpp
intel: intel-sycl-f32-depth-anything-cpp
metal: metal-depth-anything-cpp
nvidia: cuda12-depth-anything-cpp
nvidia-cuda-12: cuda12-depth-anything-cpp
nvidia-cuda-13: cuda13-depth-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp
vulkan: vulkan-depth-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-depth-anything-cpp
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-12-depth-anything-cpp
- name: cuda13-depth-anything-cpp
alias: depth-anything
license: apache-2.0
description: |
Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
using GGML. Loads pre-built GGUF weights and, given an image, returns a
dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
(3x3). No Python at inference (purego, cgo-less).
urls:
- https://github.com/mudler/depth-anything.cpp
- https://huggingface.co/depth-anything/Depth-Anything-V3
tags:
- depth-estimation
- camera-pose
- depth-anything
- gpu
- cpu
capabilities:
default: cpu-depth-anything-cpp
intel: intel-sycl-f32-depth-anything-cpp
metal: metal-depth-anything-cpp
nvidia: cuda12-depth-anything-cpp
nvidia-cuda-12: cuda12-depth-anything-cpp
nvidia-cuda-13: cuda13-depth-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp
vulkan: vulkan-depth-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-depth-anything-cpp
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-13-depth-anything-cpp
- name: cuda13-depth-anything-cpp-development
alias: depth-anything
license: apache-2.0
description: |
Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
using GGML. Loads pre-built GGUF weights and, given an image, returns a
dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
(3x3). No Python at inference (purego, cgo-less).
urls:
- https://github.com/mudler/depth-anything.cpp
- https://huggingface.co/depth-anything/Depth-Anything-V3
tags:
- depth-estimation
- camera-pose
- depth-anything
- gpu
- cpu
capabilities:
default: cpu-depth-anything-cpp
intel: intel-sycl-f32-depth-anything-cpp
metal: metal-depth-anything-cpp
nvidia: cuda12-depth-anything-cpp
nvidia-cuda-12: cuda12-depth-anything-cpp
nvidia-cuda-13: cuda13-depth-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp
vulkan: vulkan-depth-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-depth-anything-cpp
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-13-depth-anything-cpp
- name: nvidia-l4t-arm64-depth-anything-cpp
alias: depth-anything
license: apache-2.0
description: |
Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
using GGML. Loads pre-built GGUF weights and, given an image, returns a
dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
(3x3). No Python at inference (purego, cgo-less).
urls:
- https://github.com/mudler/depth-anything.cpp
- https://huggingface.co/depth-anything/Depth-Anything-V3
tags:
- depth-estimation
- camera-pose
- depth-anything
- gpu
- cpu
capabilities:
default: cpu-depth-anything-cpp
intel: intel-sycl-f32-depth-anything-cpp
metal: metal-depth-anything-cpp
nvidia: cuda12-depth-anything-cpp
nvidia-cuda-12: cuda12-depth-anything-cpp
nvidia-cuda-13: cuda13-depth-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp
vulkan: vulkan-depth-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-depth-anything-cpp
mirrors:
- localai/localai-backends:latest-nvidia-l4t-arm64-depth-anything-cpp
- name: nvidia-l4t-arm64-depth-anything-cpp-development
alias: depth-anything
license: apache-2.0
description: |
Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
using GGML. Loads pre-built GGUF weights and, given an image, returns a
dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
(3x3). No Python at inference (purego, cgo-less).
urls:
- https://github.com/mudler/depth-anything.cpp
- https://huggingface.co/depth-anything/Depth-Anything-V3
tags:
- depth-estimation
- camera-pose
- depth-anything
- gpu
- cpu
capabilities:
default: cpu-depth-anything-cpp
intel: intel-sycl-f32-depth-anything-cpp
metal: metal-depth-anything-cpp
nvidia: cuda12-depth-anything-cpp
nvidia-cuda-12: cuda12-depth-anything-cpp
nvidia-cuda-13: cuda13-depth-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp
vulkan: vulkan-depth-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-depth-anything-cpp
mirrors:
- localai/localai-backends:master-nvidia-l4t-arm64-depth-anything-cpp
- name: cuda13-nvidia-l4t-arm64-depth-anything-cpp
alias: depth-anything
license: apache-2.0
description: |
Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
using GGML. Loads pre-built GGUF weights and, given an image, returns a
dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
(3x3). No Python at inference (purego, cgo-less).
urls:
- https://github.com/mudler/depth-anything.cpp
- https://huggingface.co/depth-anything/Depth-Anything-V3
tags:
- depth-estimation
- camera-pose
- depth-anything
- gpu
- cpu
capabilities:
default: cpu-depth-anything-cpp
intel: intel-sycl-f32-depth-anything-cpp
metal: metal-depth-anything-cpp
nvidia: cuda12-depth-anything-cpp
nvidia-cuda-12: cuda12-depth-anything-cpp
nvidia-cuda-13: cuda13-depth-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp
vulkan: vulkan-depth-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-depth-anything-cpp
mirrors:
- localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-depth-anything-cpp
- name: cuda13-nvidia-l4t-arm64-depth-anything-cpp-development
alias: depth-anything
license: apache-2.0
description: |
Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
using GGML. Loads pre-built GGUF weights and, given an image, returns a
dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
(3x3). No Python at inference (purego, cgo-less).
urls:
- https://github.com/mudler/depth-anything.cpp
- https://huggingface.co/depth-anything/Depth-Anything-V3
tags:
- depth-estimation
- camera-pose
- depth-anything
- gpu
- cpu
capabilities:
default: cpu-depth-anything-cpp
intel: intel-sycl-f32-depth-anything-cpp
metal: metal-depth-anything-cpp
nvidia: cuda12-depth-anything-cpp
nvidia-cuda-12: cuda12-depth-anything-cpp
nvidia-cuda-13: cuda13-depth-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp
vulkan: vulkan-depth-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-depth-anything-cpp
mirrors:
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-depth-anything-cpp
- name: intel-sycl-f32-depth-anything-cpp
alias: depth-anything
license: apache-2.0
description: |
Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
using GGML. Loads pre-built GGUF weights and, given an image, returns a
dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
(3x3). No Python at inference (purego, cgo-less).
urls:
- https://github.com/mudler/depth-anything.cpp
- https://huggingface.co/depth-anything/Depth-Anything-V3
tags:
- depth-estimation
- camera-pose
- depth-anything
- gpu
- cpu
capabilities:
default: cpu-depth-anything-cpp
intel: intel-sycl-f32-depth-anything-cpp
metal: metal-depth-anything-cpp
nvidia: cuda12-depth-anything-cpp
nvidia-cuda-12: cuda12-depth-anything-cpp
nvidia-cuda-13: cuda13-depth-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp
vulkan: vulkan-depth-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-depth-anything-cpp
mirrors:
- localai/localai-backends:latest-gpu-intel-sycl-f32-depth-anything-cpp
- name: intel-sycl-f32-depth-anything-cpp-development
alias: depth-anything
license: apache-2.0
description: |
Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
using GGML. Loads pre-built GGUF weights and, given an image, returns a
dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
(3x3). No Python at inference (purego, cgo-less).
urls:
- https://github.com/mudler/depth-anything.cpp
- https://huggingface.co/depth-anything/Depth-Anything-V3
tags:
- depth-estimation
- camera-pose
- depth-anything
- gpu
- cpu
capabilities:
default: cpu-depth-anything-cpp
intel: intel-sycl-f32-depth-anything-cpp
metal: metal-depth-anything-cpp
nvidia: cuda12-depth-anything-cpp
nvidia-cuda-12: cuda12-depth-anything-cpp
nvidia-cuda-13: cuda13-depth-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp
vulkan: vulkan-depth-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-depth-anything-cpp
mirrors:
- localai/localai-backends:master-gpu-intel-sycl-f32-depth-anything-cpp
- name: intel-sycl-f16-depth-anything-cpp
alias: depth-anything
license: apache-2.0
description: |
Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
using GGML. Loads pre-built GGUF weights and, given an image, returns a
dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
(3x3). No Python at inference (purego, cgo-less).
urls:
- https://github.com/mudler/depth-anything.cpp
- https://huggingface.co/depth-anything/Depth-Anything-V3
tags:
- depth-estimation
- camera-pose
- depth-anything
- gpu
- cpu
capabilities:
default: cpu-depth-anything-cpp
intel: intel-sycl-f32-depth-anything-cpp
metal: metal-depth-anything-cpp
nvidia: cuda12-depth-anything-cpp
nvidia-cuda-12: cuda12-depth-anything-cpp
nvidia-cuda-13: cuda13-depth-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp
vulkan: vulkan-depth-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-depth-anything-cpp
mirrors:
- localai/localai-backends:latest-gpu-intel-sycl-f16-depth-anything-cpp
- name: intel-sycl-f16-depth-anything-cpp-development
alias: depth-anything
license: apache-2.0
description: |
Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
using GGML. Loads pre-built GGUF weights and, given an image, returns a
dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
(3x3). No Python at inference (purego, cgo-less).
urls:
- https://github.com/mudler/depth-anything.cpp
- https://huggingface.co/depth-anything/Depth-Anything-V3
tags:
- depth-estimation
- camera-pose
- depth-anything
- gpu
- cpu
capabilities:
default: cpu-depth-anything-cpp
intel: intel-sycl-f32-depth-anything-cpp
metal: metal-depth-anything-cpp
nvidia: cuda12-depth-anything-cpp
nvidia-cuda-12: cuda12-depth-anything-cpp
nvidia-cuda-13: cuda13-depth-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp
vulkan: vulkan-depth-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-depth-anything-cpp
mirrors:
- localai/localai-backends:master-gpu-intel-sycl-f16-depth-anything-cpp
- name: vulkan-depth-anything-cpp
alias: depth-anything
license: apache-2.0
description: |
Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
using GGML. Loads pre-built GGUF weights and, given an image, returns a
dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
(3x3). No Python at inference (purego, cgo-less).
urls:
- https://github.com/mudler/depth-anything.cpp
- https://huggingface.co/depth-anything/Depth-Anything-V3
tags:
- depth-estimation
- camera-pose
- depth-anything
- gpu
- cpu
capabilities:
default: cpu-depth-anything-cpp
intel: intel-sycl-f32-depth-anything-cpp
metal: metal-depth-anything-cpp
nvidia: cuda12-depth-anything-cpp
nvidia-cuda-12: cuda12-depth-anything-cpp
nvidia-cuda-13: cuda13-depth-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp
vulkan: vulkan-depth-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-depth-anything-cpp
mirrors:
- localai/localai-backends:latest-gpu-vulkan-depth-anything-cpp
- name: vulkan-depth-anything-cpp-development
alias: depth-anything
license: apache-2.0
description: |
Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
using GGML. Loads pre-built GGUF weights and, given an image, returns a
dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
(3x3). No Python at inference (purego, cgo-less).
urls:
- https://github.com/mudler/depth-anything.cpp
- https://huggingface.co/depth-anything/Depth-Anything-V3
tags:
- depth-estimation
- camera-pose
- depth-anything
- gpu
- cpu
capabilities:
default: cpu-depth-anything-cpp
intel: intel-sycl-f32-depth-anything-cpp
metal: metal-depth-anything-cpp
nvidia: cuda12-depth-anything-cpp
nvidia-cuda-12: cuda12-depth-anything-cpp
nvidia-cuda-13: cuda13-depth-anything-cpp
nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp
vulkan: vulkan-depth-anything-cpp
uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-depth-anything-cpp
mirrors:
- localai/localai-backends:master-gpu-vulkan-depth-anything-cpp
- name: vllm
alias: vllm
license: apache-2.0
icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png
description: |
vLLM is a fast and easy-to-use library for LLM inference and serving.
Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry.
vLLM is fast with:
State-of-the-art serving throughput
Efficient management of attention key and value memory with PagedAttention
Continuous batching of incoming requests
Fast model execution with CUDA/HIP graph
Quantizations: GPTQ, AWQ, AutoRound, INT4, INT8, and FP8
Optimized CUDA kernels, including integration with FlashAttention and FlashInfer
Speculative decoding
Chunked prefill
urls:
- https://github.com/vllm-project/vllm
tags:
- text-to-text
- multimodal
- GPTQ
- AWQ
- AutoRound
- INT4
- INT8
- FP8
capabilities:
amd: rocm-vllm
cpu: cpu-vllm
intel: intel-vllm
metal: metal-vllm
nvidia: cuda12-vllm
nvidia-cuda-12: cuda12-vllm
nvidia-cuda-13: cuda13-vllm
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm
- name: sglang
alias: sglang
license: apache-2.0
icon: https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png
description: |
SGLang is a fast serving framework for large language models and vision language models.
It co-designs the backend runtime (RadixAttention, continuous batching, structured
decoding) and the frontend language to make interaction with models faster and more
controllable. Features include fast backend runtime, flexible frontend language,
extensive model support, and an active community.
urls:
- https://github.com/sgl-project/sglang
tags:
- text-to-text
- multimodal
capabilities:
amd: rocm-sglang
cpu: cpu-sglang
intel: intel-sglang
nvidia: cuda12-sglang
nvidia-cuda-12: cuda12-sglang
nvidia-cuda-13: cuda13-sglang
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sglang
- name: vllm-omni
alias: vllm-omni
license: apache-2.0
icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png
description: |
vLLM-Omni is a unified interface for multimodal generation with vLLM.
It supports image generation (text-to-image, image editing), video generation
(text-to-video, image-to-video), text generation with multimodal inputs, and
text-to-speech generation. Only supports NVIDIA (CUDA) and ROCm platforms.
urls:
- https://github.com/vllm-project/vllm-omni
tags:
- text-to-image
- image-generation
- text-to-video
- video-generation
- text-to-speech
- TTS
- multimodal
- LLM
capabilities:
amd: rocm-vllm-omni
nvidia: cuda12-vllm-omni
nvidia-cuda-12: cuda12-vllm-omni
nvidia-cuda-13: cuda13-vllm-omni
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm-omni
- name: longcat-video
alias: longcat-video
license: mit
icon: https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/main/assets/longcat-video_logo.svg
description: |
LongCat-Video generation for text, image, and audio-conditioned avatars.
Supports LongCat-Video and LongCat-Video-Avatar-1.5, including multi-segment
talking-head continuation and an SDPA path for NVIDIA Blackwell ARM64 systems.
Requires Linux with an NVIDIA CUDA GPU; CPU, ROCm, and macOS are unsupported.
urls:
- https://github.com/meituan-longcat/LongCat-Video
tags:
- text-to-video
- image-to-video
- audio-to-video
- avatar-generation
- video-generation
- CUDA
capabilities:
nvidia: cuda12-longcat-video
nvidia-cuda-12: cuda12-longcat-video
nvidia-cuda-13: cuda13-longcat-video
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-longcat-video
- name: mlx
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run LLMs with MLX
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
capabilities:
default: cpu-mlx
metal: metal-mlx
nvidia: cuda12-mlx
nvidia-cuda-12: cuda12-mlx
nvidia-cuda-13: cuda13-mlx
nvidia-l4t: nvidia-l4t-mlx
nvidia-l4t-cuda-12: nvidia-l4t-mlx
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx
- name: mlx-video
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Generate videos with LTX-2 and converted Wan2.1/Wan2.2 checkpoints using
MLX on Apple Silicon.
urls:
- https://github.com/Blaizzy/mlx-video
tags:
- text-to-video
- image-to-video
- MLX
capabilities:
metal: metal-mlx-video
- name: mlx-vlm
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Vision-Language Models with MLX
urls:
- https://github.com/Blaizzy/mlx-vlm
tags:
- text-to-text
- multimodal
- vision-language
- LLM
- MLX
capabilities:
default: cpu-mlx-vlm
metal: metal-mlx-vlm
nvidia: cuda12-mlx-vlm
nvidia-cuda-12: cuda12-mlx-vlm
nvidia-cuda-13: cuda13-mlx-vlm
nvidia-l4t: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm
- name: mlx-audio
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Audio Models with MLX
urls:
- https://github.com/Blaizzy/mlx-audio
tags:
- audio-to-text
- audio-generation
- text-to-audio
- LLM
- MLX
capabilities:
default: cpu-mlx-audio
metal: metal-mlx-audio
nvidia: cuda12-mlx-audio
nvidia-cuda-12: cuda12-mlx-audio
nvidia-cuda-13: cuda13-mlx-audio
nvidia-l4t: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio
- name: mlx-distributed
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run distributed LLM inference with MLX across multiple Apple Silicon Macs
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
- distributed
capabilities:
default: cpu-mlx-distributed
metal: metal-mlx-distributed
nvidia: cuda12-mlx-distributed
nvidia-cuda-12: cuda12-mlx-distributed
nvidia-cuda-13: cuda13-mlx-distributed
nvidia-l4t: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed
- name: rerankers
alias: rerankers
capabilities:
amd: rocm-rerankers
intel: intel-rerankers
metal: metal-rerankers
nvidia: cuda12-rerankers
- name: tinygrad
alias: tinygrad
license: MIT
description: |
tinygrad is a minimalist deep-learning framework with zero runtime
dependencies that targets CUDA, ROCm, Metal, WebGPU and CPU (CLANG).
The LocalAI tinygrad backend exposes a single multimodal runtime that
covers LLM text generation (Llama / Qwen / Mistral via safetensors or
GGUF) with native tool-call extraction, BERT-family embeddings,
Stable Diffusion 1.x / 2 / XL image generation, and Whisper speech-to-text.
Single image: tinygrad generates its own GPU kernels and dlopens the
host driver libraries at runtime, so there is no per-toolkit build
split. The same image runs CPU-only or accelerates against
CUDA / ROCm / Metal when the host driver is visible.
urls:
- https://github.com/tinygrad/tinygrad
tags:
- text-to-text
- LLM
- embeddings
- image-generation
- transcription
- multimodal
uri: quay.io/go-skynet/local-ai-backends:latest-tinygrad
mirrors:
- localai/localai-backends:latest-tinygrad
- name: transformers
alias: transformers
license: apache-2.0
icon: https://avatars.githubusercontent.com/u/25720743?s=200&v=4
description: |
Transformers acts as the model-definition framework for state-of-the-art machine learning models in text, computer vision, audio, video, and multimodal model, for both inference and training.
It centralizes the model definition so that this definition is agreed upon across the ecosystem. transformers is the pivot across frameworks: if a model definition is supported, it will be compatible with the majority of training frameworks (Axolotl, Unsloth, DeepSpeed, FSDP, PyTorch-Lightning, ...), inference engines (vLLM, SGLang, TGI, ...), and adjacent modeling libraries (llama.cpp, mlx, ...) which leverage the model definition from transformers.
urls:
- https://github.com/huggingface/transformers
tags:
- text-to-text
- multimodal
capabilities:
amd: rocm-transformers
intel: intel-transformers
metal: metal-transformers
nvidia: cuda12-transformers
nvidia-cuda-12: cuda12-transformers
nvidia-cuda-13: cuda13-transformers
- name: diffusers
alias: diffusers
license: apache-2.0
icon: https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg
description: "\U0001F917 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, \U0001F917 Diffusers is a modular toolbox that supports both.\n"
urls:
- https://github.com/huggingface/diffusers
tags:
- image-generation
- video-generation
- sound-generation
- diffusion-models
capabilities:
amd: rocm-diffusers
default: cpu-diffusers
intel: intel-diffusers
metal: metal-diffusers
nvidia: cuda12-diffusers
nvidia-cuda-12: cuda12-diffusers
nvidia-cuda-13: cuda13-diffusers
nvidia-l4t: nvidia-l4t-diffusers
nvidia-l4t-cuda-12: nvidia-l4t-diffusers
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-diffusers
- name: ace-step
alias: ace-step
description: |
ACE-Step 1.5 is an open-source music generation model. It supports simple mode (natural language description) and advanced mode (caption, lyrics, think, bpm, keyscale, etc.). Uses in-process acestep (LLMHandler for metadata, DiT for audio).
urls:
- https://github.com/ace-step/ACE-Step-1.5
tags:
- music-generation
- sound-generation
capabilities:
amd: rocm-ace-step
default: cpu-ace-step
intel: intel-ace-step
metal: metal-ace-step
nvidia: cuda12-ace-step
nvidia-cuda-12: cuda12-ace-step
nvidia-cuda-13: cuda13-ace-step
- name: ace-step-development
alias: ace-step
description: |
ACE-Step 1.5 is an open-source music generation model. It supports simple mode (natural language description) and advanced mode (caption, lyrics, think, bpm, keyscale, etc.). Uses in-process acestep (LLMHandler for metadata, DiT for audio).
urls:
- https://github.com/ace-step/ACE-Step-1.5
tags:
- music-generation
- sound-generation
capabilities:
amd: rocm-ace-step-development
default: cpu-ace-step-development
intel: intel-ace-step-development
metal: metal-ace-step-development
nvidia: cuda12-ace-step-development
nvidia-cuda-12: cuda12-ace-step-development
nvidia-cuda-13: cuda13-ace-step-development
- name: acestep-cpp
alias: acestep-cpp
description: |
ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends.
Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE).
urls:
- https://github.com/ace-step/acestep.cpp
tags:
- music-generation
- sound-generation
capabilities:
amd: rocm-acestep-cpp
default: cpu-acestep-cpp
intel: intel-sycl-f16-acestep-cpp
metal: metal-acestep-cpp
nvidia: cuda12-acestep-cpp
nvidia-cuda-12: cuda12-acestep-cpp
nvidia-cuda-13: cuda13-acestep-cpp
nvidia-l4t: nvidia-l4t-arm64-acestep-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp
vulkan: vulkan-acestep-cpp
- name: qwen3-tts-cpp
alias: qwen3-tts-cpp
description: |
Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech
with streaming output, named speakers, voice design, and zero-shot voice
cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B
models in Q8_0 / Q4_K_M.
urls:
- https://github.com/ServeurpersoCom/qwentts.cpp
tags:
- text-to-speech
- tts
- voice-cloning
- streaming
capabilities:
amd: rocm-qwen3-tts-cpp
default: cpu-qwen3-tts-cpp
intel: intel-sycl-f16-qwen3-tts-cpp
metal: metal-qwen3-tts-cpp
nvidia: cuda12-qwen3-tts-cpp
nvidia-cuda-12: cuda12-qwen3-tts-cpp
nvidia-cuda-13: cuda13-qwen3-tts-cpp
nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp
vulkan: vulkan-qwen3-tts-cpp
- name: moss-tts-cpp
alias: moss-tts-cpp
description: |
MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech
for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local
transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a
self-contained GGUF with no Python at inference time. 48kHz stereo output
with reference-audio voice cloning.
urls:
- https://github.com/mudler/moss-tts.cpp
- https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF
tags:
- text-to-speech
- tts
- voice-cloning
capabilities:
amd: rocm-moss-tts-cpp
default: cpu-moss-tts-cpp
intel: intel-sycl-f16-moss-tts-cpp
metal: metal-moss-tts-cpp
nvidia: cuda12-moss-tts-cpp
nvidia-cuda-12: cuda12-moss-tts-cpp
nvidia-cuda-13: cuda13-moss-tts-cpp
nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp
vulkan: vulkan-moss-tts-cpp
- name: moss-tts-cpp-development
alias: moss-tts-cpp
description: |
MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech
for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local
transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a
self-contained GGUF with no Python at inference time. 48kHz stereo output
with reference-audio voice cloning.
urls:
- https://github.com/mudler/moss-tts.cpp
- https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF
tags:
- text-to-speech
- tts
- voice-cloning
capabilities:
amd: rocm-moss-tts-cpp-development
default: cpu-moss-tts-cpp-development
intel: intel-sycl-f16-moss-tts-cpp-development
metal: metal-moss-tts-cpp-development
nvidia: cuda12-moss-tts-cpp-development
nvidia-cuda-12: cuda12-moss-tts-cpp-development
nvidia-cuda-13: cuda13-moss-tts-cpp-development
nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp-development
nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp-development
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp-development
vulkan: vulkan-moss-tts-cpp-development
- name: magpie-tts-cpp
alias: magpie-tts-cpp
description: |
Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++
text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder +
autoregressive decoder over NanoCodec tokens), running from a single
self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no
Python at inference time. 22.05kHz mono output, 5 baked voices (Aria,
Jason, John, Leo, Sofia), 9+ languages.
urls:
- https://github.com/mudler/magpie-tts.cpp
- https://huggingface.co/mudler/magpie-tts.cpp-gguf
tags:
- text-to-speech
- tts
capabilities:
amd: rocm-magpie-tts-cpp
default: cpu-magpie-tts-cpp
intel: intel-sycl-f16-magpie-tts-cpp
metal: metal-magpie-tts-cpp
nvidia: cuda12-magpie-tts-cpp
nvidia-cuda-12: cuda12-magpie-tts-cpp
nvidia-cuda-13: cuda13-magpie-tts-cpp
nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp
vulkan: vulkan-magpie-tts-cpp
- name: magpie-tts-cpp-development
alias: magpie-tts-cpp
description: |
Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++
text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder +
autoregressive decoder over NanoCodec tokens), running from a single
self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no
Python at inference time. 22.05kHz mono output, 5 baked voices (Aria,
Jason, John, Leo, Sofia), 9+ languages.
urls:
- https://github.com/mudler/magpie-tts.cpp
- https://huggingface.co/mudler/magpie-tts.cpp-gguf
tags:
- text-to-speech
- tts
capabilities:
amd: rocm-magpie-tts-cpp-development
default: cpu-magpie-tts-cpp-development
intel: intel-sycl-f16-magpie-tts-cpp-development
metal: metal-magpie-tts-cpp-development
nvidia: cuda12-magpie-tts-cpp-development
nvidia-cuda-12: cuda12-magpie-tts-cpp-development
nvidia-cuda-13: cuda13-magpie-tts-cpp-development
nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp-development
nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp-development
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp-development
vulkan: vulkan-magpie-tts-cpp-development
- name: omnivoice-cpp
alias: omnivoice-cpp
description: |
OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning
(reference audio + transcript) and voice design (attribute keywords: gender,
age, pitch, style, volume, emotion). 24kHz mono output, 646 languages.
Supports streaming synthesis.
urls:
- https://github.com/ServeurpersoCom/omnivoice.cpp
tags:
- text-to-speech
- tts
- voice-cloning
- voice-design
capabilities:
amd: rocm-omnivoice-cpp
default: cpu-omnivoice-cpp
intel: intel-sycl-f16-omnivoice-cpp
metal: metal-omnivoice-cpp
nvidia: cuda12-omnivoice-cpp
nvidia-cuda-12: cuda12-omnivoice-cpp
nvidia-cuda-13: cuda13-omnivoice-cpp
nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp
vulkan: vulkan-omnivoice-cpp
- name: vibevoice-cpp
alias: vibevoice-cpp
description: |
vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both
text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with
speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments.
urls:
- https://github.com/mudler/vibevoice.cpp
tags:
- text-to-speech
- tts
- speech-to-text
- asr
- voice-cloning
- diarization
capabilities:
amd: rocm-vibevoice-cpp
default: cpu-vibevoice-cpp
intel: intel-sycl-f16-vibevoice-cpp
metal: metal-vibevoice-cpp
nvidia: cuda12-vibevoice-cpp
nvidia-cuda-12: cuda12-vibevoice-cpp
nvidia-cuda-13: cuda13-vibevoice-cpp
nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp
vulkan: vulkan-vibevoice-cpp
- name: localvqe
alias: localvqe
license: apache2
description: |
LocalVQE C++ backend using GGML — joint acoustic echo cancellation, noise
suppression, and dereverberation (DeepVQE-style architecture). 16 kHz mono
in / out, supports both batch and low-latency streaming. Implements the
audio-transform capability.
urls:
- https://github.com/localai-org/LocalVQE
tags:
- audio-transform
- aec
- acoustic-echo-cancellation
- noise-suppression
- dereverberation
capabilities:
amd: vulkan-localvqe
default: cpu-localvqe
intel: vulkan-localvqe
metal: metal-localvqe
nvidia: vulkan-localvqe
nvidia-cuda-12: vulkan-localvqe
nvidia-cuda-13: vulkan-localvqe
nvidia-l4t: vulkan-localvqe
nvidia-l4t-cuda-12: vulkan-localvqe
nvidia-l4t-cuda-13: vulkan-localvqe
vulkan: vulkan-localvqe
- name: privacy-filter
alias: privacy-filter
license: apache-2.0
icon: https://cdn-avatars.huggingface.co/v1/production/uploads/5fd5e18a90b6dc4633f6d292/QPiv8pt4JNxr0FdGnpFef.png
description: |
Standalone GGML engine (privacy-filter.cpp) for the OpenMed privacy-filter
PII/NER token-classification model family. It runs the openai-privacy-filter
architecture (a gpt-oss-style sparse-MoE bidirectional token classifier) on
stock upstream GGML — no llama.cpp coupling and no Python — and serves the
TokenClassify RPC (constrained BIOES Viterbi decode into UTF-8 byte-offset
entity spans) used by LocalAI's NER PII redaction tier.
urls:
- https://github.com/localai-org/privacy-filter.cpp
tags:
- token-classification
- ner
- pii
- privacy
- CPU
- GPU
capabilities:
amd: vulkan-privacy-filter
default: cpu-privacy-filter
intel: vulkan-privacy-filter
metal: metal-privacy-filter
nvidia: vulkan-privacy-filter
nvidia-cuda-12: vulkan-privacy-filter
nvidia-cuda-13: cuda13-privacy-filter
vulkan: vulkan-privacy-filter
- name: faster-whisper
license: MIT
icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4
description: |
faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models.
This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU.
urls:
- https://github.com/SYSTRAN/faster-whisper
tags:
- speech-to-text
- Whisper
capabilities:
amd: rocm-faster-whisper
default: cpu-faster-whisper
intel: intel-faster-whisper
metal: metal-faster-whisper
nvidia: cuda12-faster-whisper
nvidia-cuda-12: cuda12-faster-whisper
nvidia-cuda-13: cuda13-faster-whisper
nvidia-l4t: nvidia-l4t-arm64-faster-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-faster-whisper
- name: whisper-medusa
alias: whisper-medusa
license: MIT
description: |
Whisper-Medusa accelerates Whisper transcription by predicting multiple tokens per decoding step.
The upstream checkpoints use custom Transformers generation code and accept audio clips up to 30 seconds.
urls:
- https://github.com/aiola-lab/whisper-medusa
- https://huggingface.co/collections/aiola/whisper-medusa
tags:
- speech-to-text
- transcription
- Whisper
- Medusa
capabilities:
default: cpu-whisper-medusa
nvidia: cuda12-whisper-medusa
nvidia-cuda-12: cuda12-whisper-medusa
- name: moonshine
alias: moonshine
license: MIT
description: |
Moonshine is a fast, accurate, and efficient speech-to-text transcription model using ONNX Runtime.
It provides real-time transcription capabilities with support for multiple model sizes and GPU acceleration.
urls:
- https://github.com/moonshine-ai/moonshine
tags:
- speech-to-text
- transcription
- ONNX
capabilities:
default: cpu-moonshine
metal: metal-moonshine
nvidia: cuda12-moonshine
nvidia-cuda-12: cuda12-moonshine
nvidia-cuda-13: cuda13-moonshine
- name: whisperx
alias: whisperx
license: BSD-4-Clause
description: |
WhisperX provides fast automatic speech recognition with word-level timestamps, speaker diarization,
and forced alignment. Built on faster-whisper and pyannote-audio for high-accuracy transcription
with speaker identification.
urls:
- https://github.com/m-bain/whisperX
tags:
- speech-to-text
- diarization
- whisperx
capabilities:
default: cpu-whisperx
metal: metal-whisperx
nvidia: cuda12-whisperx
nvidia-cuda-12: cuda12-whisperx
nvidia-cuda-13: cuda13-whisperx
nvidia-l4t: nvidia-l4t-arm64-whisperx
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisperx
- name: kokoro
alias: kokoro
license: apache-2.0
icon: https://avatars.githubusercontent.com/u/166769057?v=4
description: |
Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects.
urls:
- https://huggingface.co/hexgrad/Kokoro-82M
- https://github.com/hexgrad/kokoro
tags:
- text-to-speech
- TTS
- LLM
capabilities:
amd: rocm-kokoro
default: cpu-kokoro
intel: intel-kokoro
metal: metal-kokoro
nvidia: cuda12-kokoro
nvidia-cuda-12: cuda12-kokoro
nvidia-cuda-13: cuda13-kokoro
nvidia-l4t: nvidia-l4t-kokoro
nvidia-l4t-cuda-12: nvidia-l4t-kokoro
- name: kokoros
alias: kokoros
license: apache-2.0
icon: https://avatars.githubusercontent.com/u/166769057?v=4
description: |
Kokoros is a pure Rust TTS backend using the Kokoro ONNX model (82M parameters).
It provides fast, high-quality text-to-speech with streaming support, built on
ONNX Runtime for efficient CPU inference. Supports English, Japanese, Mandarin
Chinese, and German.
urls:
- https://huggingface.co/hexgrad/Kokoro-82M
- https://github.com/lucasjinreal/Kokoros
tags:
- text-to-speech
- TTS
- Rust
- ONNX
capabilities:
default: cpu-kokoros
- name: coqui
alias: coqui
license: mpl-2.0
icon: https://avatars.githubusercontent.com/u/1338804?s=200&v=4
description: "\U0001F438 Coqui TTS is a library for advanced Text-to-Speech generation.\n\n\U0001F680 Pretrained models in +1100 languages.\n\n\U0001F6E0️ Tools for training new models and fine-tuning existing models in any language.\n\n\U0001F4DA Utilities for dataset analysis and curation.\n"
urls:
- https://github.com/idiap/coqui-ai-TTS
tags:
- text-to-speech
- TTS
capabilities:
amd: rocm-coqui
intel: intel-coqui
metal: metal-coqui
nvidia: cuda12-coqui
nvidia-cuda-12: cuda12-coqui
- name: outetts
alias: outetts
license: apache-2.0
description: |
OuteTTS is an open-weight text-to-speech model from OuteAI (OuteAI/OuteTTS-0.3-1B).
Supports custom speaker voices via audio path or default speakers.
urls:
- https://github.com/OuteAI/outetts
tags:
- text-to-speech
- TTS
capabilities:
default: cpu-outetts
nvidia-cuda-12: cuda12-outetts
- name: chatterbox
alias: chatterbox
license: MIT
icon: https://avatars.githubusercontent.com/u/49844015?s=200&v=4
description: |
Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations.
Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out.
urls:
- https://github.com/resemble-ai/chatterbox
tags:
- text-to-speech
- TTS
capabilities:
default: cpu-chatterbox
metal: metal-chatterbox
nvidia: cuda12-chatterbox
nvidia-cuda-12: cuda12-chatterbox
nvidia-cuda-13: cuda13-chatterbox
nvidia-l4t: nvidia-l4t-arm64-chatterbox
nvidia-l4t-cuda-12: nvidia-l4t-arm64-chatterbox
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-chatterbox
- name: vibevoice
alias: vibevoice
license: mit
icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4
description: |
VibeVoice-Realtime is a real-time text-to-speech model that generates natural-sounding speech.
urls:
- https://github.com/microsoft/VibeVoice
tags:
- text-to-speech
- TTS
capabilities:
amd: rocm-vibevoice
default: cpu-vibevoice
intel: intel-vibevoice
metal: metal-vibevoice
nvidia: cuda12-vibevoice
nvidia-cuda-12: cuda12-vibevoice
nvidia-cuda-13: cuda13-vibevoice
nvidia-l4t: nvidia-l4t-vibevoice
nvidia-l4t-cuda-12: nvidia-l4t-vibevoice
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice
- name: qwen-tts
alias: qwen-tts
license: apache-2.0
icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png
description: |
Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning.
urls:
- https://github.com/QwenLM/Qwen3-TTS
tags:
- text-to-speech
- TTS
capabilities:
amd: rocm-qwen-tts
default: cpu-qwen-tts
intel: intel-qwen-tts
metal: metal-qwen-tts
nvidia: cuda12-qwen-tts
nvidia-cuda-12: cuda12-qwen-tts
nvidia-cuda-13: cuda13-qwen-tts
nvidia-l4t: nvidia-l4t-qwen-tts
nvidia-l4t-cuda-12: nvidia-l4t-qwen-tts
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-tts
- name: fish-speech
alias: fish-speech
license: apache-2.0
icon: https://avatars.githubusercontent.com/u/148526220?s=200&v=4
description: |
Fish Speech is a high-quality text-to-speech model supporting voice cloning via reference audio.
urls:
- https://github.com/fishaudio/fish-speech
tags:
- text-to-speech
- TTS
- voice-cloning
capabilities:
amd: rocm-fish-speech
default: cpu-fish-speech
intel: intel-fish-speech
nvidia: cuda12-fish-speech
nvidia-cuda-12: cuda12-fish-speech
nvidia-cuda-13: cuda13-fish-speech
nvidia-l4t: nvidia-l4t-fish-speech
nvidia-l4t-cuda-12: nvidia-l4t-fish-speech
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-fish-speech
- name: faster-qwen3-tts
alias: faster-qwen3-tts
license: apache-2.0
icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png
description: |
Real-time Qwen3-TTS inference using CUDA graph capture. Voice clone only; requires NVIDIA GPU with CUDA.
urls:
- https://github.com/andimarafioti/faster-qwen3-tts
- https://pypi.org/project/faster-qwen3-tts/
tags:
- text-to-speech
- TTS
- voice-clone
capabilities:
default: cuda12-faster-qwen3-tts
nvidia: cuda12-faster-qwen3-tts
nvidia-cuda-12: cuda12-faster-qwen3-tts
nvidia-cuda-13: cuda13-faster-qwen3-tts
nvidia-l4t: nvidia-l4t-faster-qwen3-tts
nvidia-l4t-cuda-12: nvidia-l4t-faster-qwen3-tts
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-faster-qwen3-tts
- name: funasr
alias: funasr
license: mit
icon: https://avatars.githubusercontent.com/u/109454077
description: |
FunASR is an industrial-grade speech recognition toolkit supporting 50+ languages.
Includes SenseVoice (170x realtime, emotion detection), Paraformer (highest Chinese
accuracy), and built-in VAD, punctuation restoration, and speaker diarization.
urls:
- https://github.com/modelscope/FunASR
tags:
- speech-recognition
- ASR
- multilingual
capabilities:
amd: rocm-funasr
default: cpu-funasr
intel: intel-funasr
metal: metal-funasr
nvidia: cuda12-funasr
nvidia-cuda-12: cuda12-funasr
nvidia-cuda-13: cuda13-funasr
nvidia-l4t: nvidia-l4t-funasr
nvidia-l4t-cuda-12: nvidia-l4t-funasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-funasr
- name: qwen-asr
alias: qwen-asr
license: apache-2.0
icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png
description: |
Qwen3-ASR is an automatic speech recognition model supporting multiple languages and batch inference.
urls:
- https://github.com/QwenLM/Qwen3-ASR
tags:
- speech-recognition
- ASR
capabilities:
amd: rocm-qwen-asr
default: cpu-qwen-asr
intel: intel-qwen-asr
metal: metal-qwen-asr
nvidia: cuda12-qwen-asr
nvidia-cuda-12: cuda12-qwen-asr
nvidia-cuda-13: cuda13-qwen-asr
nvidia-l4t: nvidia-l4t-qwen-asr
nvidia-l4t-cuda-12: nvidia-l4t-qwen-asr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-asr
- name: nemo
alias: nemo
license: apache-2.0
icon: https://www.nvidia.com/favicon.ico
description: |
NVIDIA NEMO Toolkit for ASR provides state-of-the-art automatic speech recognition models including Parakeet models for various languages and use cases.
urls:
- https://github.com/NVIDIA/NeMo
tags:
- speech-recognition
- ASR
- NVIDIA
capabilities:
amd: rocm-nemo
default: cpu-nemo
intel: intel-nemo
metal: metal-nemo
nvidia: cuda12-nemo
nvidia-cuda-12: cuda12-nemo
nvidia-cuda-13: cuda13-nemo
- name: voxcpm
alias: voxcpm
license: mit
icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4
description: |
VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech.
urls:
- https://github.com/ModelBest/VoxCPM
tags:
- text-to-speech
- TTS
capabilities:
amd: rocm-voxcpm
default: cpu-voxcpm
intel: intel-voxcpm
metal: metal-voxcpm
nvidia: cuda12-voxcpm
nvidia-cuda-12: cuda12-voxcpm
nvidia-cuda-13: cuda13-voxcpm
- name: pocket-tts
alias: pocket-tts
license: mit
icon: https://avatars.githubusercontent.com/u/151010778?s=200&v=4
description: |
Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs.
urls:
- https://github.com/kyutai-labs/pocket-tts
tags:
- text-to-speech
- TTS
capabilities:
amd: rocm-pocket-tts
default: cpu-pocket-tts
intel: intel-pocket-tts
metal: metal-pocket-tts
nvidia: cuda12-pocket-tts
nvidia-cuda-12: cuda12-pocket-tts
nvidia-cuda-13: cuda13-pocket-tts
nvidia-l4t: nvidia-l4t-pocket-tts
nvidia-l4t-cuda-12: nvidia-l4t-pocket-tts
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-pocket-tts
- name: piper
license: MIT
icon: https://github.com/OHF-Voice/piper1-gpl/raw/main/etc/logo.png
description: |
A fast, local neural text to speech system
urls:
- https://github.com/rhasspy/piper
- https://github.com/mudler/go-piper
tags:
- text-to-speech
- TTS
capabilities:
default: cpu-piper
metal: metal-piper
- name: opus
alias: opus
license: BSD-3-Clause
description: |
Opus audio codec backend for encoding and decoding audio.
Required for WebRTC transport in the Realtime API.
urls:
- https://opus-codec.org/
tags:
- audio-codec
- opus
- WebRTC
- realtime
capabilities:
default: cpu-opus
metal: metal-opus
- name: opus-development
alias: opus
license: BSD-3-Clause
description: |
Opus audio codec backend for encoding and decoding audio.
Required for WebRTC transport in the Realtime API.
urls:
- https://opus-codec.org/
tags:
- audio-codec
- opus
- WebRTC
- realtime
capabilities:
default: cpu-opus-development
metal: metal-opus-development
- name: silero-vad
icon: https://user-images.githubusercontent.com/12515440/89997349-b3523080-dc94-11ea-9906-ca2e8bc50535.png
description: |
Silero VAD: pre-trained enterprise-grade Voice Activity Detector.
Silero VAD is a voice activity detection model that can be used to detect whether a given audio contains speech or not.
urls:
- https://github.com/snakers4/silero-vad
tags:
- voice-activity-detection
- VAD
- silero-vad
- CPU
capabilities:
default: cpu-silero-vad
metal: metal-silero-vad
- name: local-store
license: MIT
description: |
Local Store is a local-first, self-hosted, and open-source vector database.
urls:
- https://github.com/mudler/LocalAI
tags:
- vector-database
- local-first
- open-source
- CPU
capabilities:
default: cpu-local-store
metal: metal-local-store
- name: cloud-proxy
alias: cloud-proxy
license: MIT
description: |
Forward OpenAI-compatible and Anthropic chat requests to external providers.
urls:
- https://github.com/mudler/LocalAI/tree/master/backend/go/cloud-proxy
tags:
- text-to-text
- cloud
- proxy
- CPU
capabilities:
default: cpu-cloud-proxy
metal: metal-cloud-proxy
- name: localai-proxy
alias: localai-proxy
license: MIT
description: |
Serve a model from another LocalAI instance: text, embeddings, rerank, audio, image and video requests are forwarded to its REST API.
urls:
- https://github.com/mudler/LocalAI/tree/master/backend/go/localai-proxy
tags:
- text-to-text
- proxy
- CPU
capabilities:
default: cpu-localai-proxy
metal: metal-localai-proxy
- name: valkey-store
license: MIT
description: |
Valkey Store is a Valkey Search (FT.*) backed vector store for LocalAI. It
persists vectors across restarts and supports opt-in HNSW indexing. Requires
a reachable Valkey Search server (valkey/valkey-bundle).
urls:
- https://github.com/mudler/LocalAI
tags:
- vector-database
- valkey
- open-source
- CPU
capabilities:
default: cpu-valkey-store
metal: metal-valkey-store
- name: qdrant-store
license: MIT
description: |
Qdrant Store is a Qdrant-backed vector store for LocalAI. It persists
vectors across restarts in HNSW-indexed collections and works with
self-hosted Qdrant (single node or cluster) and Qdrant Cloud. Requires a
reachable Qdrant server (gRPC port, 6334 by default).
urls:
- https://github.com/mudler/LocalAI
- https://github.com/qdrant/qdrant
tags:
- vector-database
- qdrant
- open-source
- CPU
capabilities:
default: cpu-qdrant-store
metal: metal-qdrant-store
- name: kitten-tts
license: apache-2.0
description: |
Kitten TTS is a text-to-speech model that can generate speech from text.
urls:
- https://github.com/KittenML/KittenTTS
tags:
- text-to-speech
- TTS
capabilities:
default: cpu-kitten-tts
metal: metal-kitten-tts
- name: neutts
license: apache-2.0
description: |
NeuTTS Air is the world’s first super-realistic, on-device, TTS speech language model with instant voice cloning. Built off a 0.5B LLM backbone, NeuTTS Air brings natural-sounding speech, real-time performance, built-in security and speaker cloning to your local device - unlocking a new category of embedded voice agents, assistants, toys, and compliance-safe apps.
urls:
- https://github.com/neuphonic/neutts-air
tags:
- text-to-speech
- TTS
capabilities:
amd: rocm-neutts
default: cpu-neutts
nvidia: cuda12-neutts
nvidia-cuda-12: cuda12-neutts
- name: sherpa-onnx
alias: sherpa-onnx
description: |
Sherpa-ONNX backend for text-to-speech (VITS, Matcha, Kokoro), speech-to-text (Whisper, Paraformer, SenseVoice, Omnilingual ASR CTC), and voice activity detection via ONNX Runtime.
Supports multi-speaker voices, 1600+ language ASR, and GPU acceleration.
urls:
- https://k2-fsa.github.io/sherpa/onnx/
tags:
- text-to-speech
- TTS
- speech-to-text
- ASR
capabilities:
default: cpu-sherpa-onnx
metal: metal-sherpa-onnx
nvidia: cuda12-sherpa-onnx
nvidia-cuda-12: cuda12-sherpa-onnx
- name: supertonic
alias: supertonic
description: |
Supertonic backend: lightning-fast, on-device multilingual text-to-speech via ONNX Runtime.
Runs Supertone's flow-matching TTS model (Supertone/supertonic-3), 44.1kHz output, 31 languages,
multiple preset voice styles. No espeak-ng dependency.
urls:
- https://github.com/supertone-inc/supertonic
tags:
- text-to-speech
- TTS
capabilities:
default: cpu-supertonic
metal: metal-supertonic
- name: neutts-development
license: apache-2.0
description: |
NeuTTS Air is the world’s first super-realistic, on-device, TTS speech language model with instant voice cloning. Built off a 0.5B LLM backbone, NeuTTS Air brings natural-sounding speech, real-time performance, built-in security and speaker cloning to your local device - unlocking a new category of embedded voice agents, assistants, toys, and compliance-safe apps.
urls:
- https://github.com/neuphonic/neutts-air
tags:
- text-to-speech
- TTS
capabilities:
amd: rocm-neutts-development
default: cpu-neutts-development
nvidia: cuda12-neutts-development
nvidia-cuda-12: cuda12-neutts-development
- name: llama-cpp-development
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp-development
default: cpu-llama-cpp-development
intel: intel-sycl-f16-llama-cpp-development
metal: metal-llama-cpp-development
nvidia: cuda12-llama-cpp-development
nvidia-cuda-12: cuda12-llama-cpp-development
nvidia-cuda-13: cuda13-llama-cpp-development
nvidia-l4t: nvidia-l4t-arm64-llama-cpp-development
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp-development
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp-development
vulkan: vulkan-llama-cpp-development
- name: ik-llama-cpp-development
alias: ik-llama-cpp
license: mit
description: |
Fork of llama.cpp optimized for CPU performance by ikawrakow
urls:
- https://github.com/ikawrakow/ik_llama.cpp
tags:
- text-to-text
- LLM
- CPU
capabilities:
default: cpu-ik-llama-cpp-development
- name: turboquant-development
alias: turboquant
license: mit
description: |
Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme.
Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama.
urls:
- https://github.com/TheTom/llama-cpp-turboquant
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- turboquant
- kv-cache
capabilities:
amd: rocm-turboquant-development
default: cpu-turboquant-development
intel: intel-sycl-f16-turboquant-development
nvidia: cuda12-turboquant-development
nvidia-cuda-12: cuda12-turboquant-development
nvidia-cuda-13: cuda13-turboquant-development
nvidia-l4t: nvidia-l4t-arm64-turboquant-development
nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant-development
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant-development
vulkan: vulkan-turboquant-development
- name: bonsai-development
alias: bonsai
license: apache-2.0
description: |
Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit)
weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses
the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives
these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp
backend.
urls:
- https://github.com/PrismML-Eng/llama.cpp
- https://huggingface.co/prism-ml
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- bonsai
- 1-bit
- ternary
capabilities:
amd: rocm-bonsai-development
default: cpu-bonsai-development
intel: intel-sycl-f16-bonsai-development
nvidia: cuda12-bonsai-development
nvidia-cuda-12: cuda12-bonsai-development
nvidia-cuda-13: cuda13-bonsai-development
nvidia-l4t: nvidia-l4t-arm64-bonsai-development
nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai-development
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai-development
vulkan: vulkan-bonsai-development
- name: ds4-development
alias: ds4
license: mit
description: |
antirez/ds4 - DeepSeek V4 Flash inference engine. Single-model,
optimized for Metal (Darwin) and CUDA (Linux). Requires the GGUFs
published at huggingface.co/antirez/deepseek-v4-gguf.
urls:
- https://github.com/antirez/ds4
tags:
- text-to-text
- LLM
- CPU
- CUDA
- Metal
capabilities:
default: cpu-ds4-development
metal: metal-ds4-development
metal-darwin-arm64: metal-ds4-development
nvidia: cuda13-ds4-development
nvidia-cuda-13: cuda13-ds4-development
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ds4-development
- name: audio-cpp-development
alias: audio-cpp
license: apache-2.0
description: |
0xShug0/audio.cpp - a ggml audio inference framework covering text to
speech, voice cloning, transcription, forced alignment, voice activity
detection, speaker diarization, source separation, voice conversion and
music generation, across 30+ model families. Consumes audio.cpp-native
GGUF packages from huggingface.co/audio-cpp/audio.cpp-gguf.
urls:
- https://github.com/0xShug0/audio.cpp
- https://huggingface.co/audio-cpp/audio.cpp-gguf
tags:
- TTS
- text-to-speech
- audio-transcription
- CPU
- CUDA
- HIP
- Metal
capabilities:
amd: rocm-audio-cpp-development
default: cpu-audio-cpp-development
metal: metal-audio-cpp-development
metal-darwin-arm64: metal-audio-cpp-development
nvidia: cuda12-audio-cpp-development
nvidia-cuda-12: cuda12-audio-cpp-development
nvidia-cuda-13: cuda13-audio-cpp-development
- name: stablediffusion-ggml-development
alias: stablediffusion-ggml
license: mit
icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png
description: |
Stable Diffusion and Flux in pure C/C++
urls:
- https://github.com/leejet/stable-diffusion.cpp
tags:
- image-generation
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-stablediffusion-ggml-development
default: cpu-stablediffusion-ggml-development
intel: intel-sycl-f16-stablediffusion-ggml-development
metal: metal-stablediffusion-ggml-development
nvidia: cuda12-stablediffusion-ggml-development
nvidia-cuda-12: cuda12-stablediffusion-ggml-development
nvidia-cuda-13: cuda13-stablediffusion-ggml-development
nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml-development
nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml-development
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml-development
vulkan: vulkan-stablediffusion-ggml-development
- name: trellis2cpp-development
alias: trellis2cpp
license: mit
description: |
TRELLIS.2 image-to-3D generation (GLB meshes with PBR textures) in C++/ggml
urls:
- https://github.com/localai-org/trellis2cpp
- https://github.com/microsoft/TRELLIS.2
tags:
- image-to-3d
- 3d-generation
- CPU
- GPU
- CUDA
- Metal
capabilities:
default: cpu-trellis2cpp-development
metal: metal-trellis2cpp-development
nvidia: cuda12-trellis2cpp-development
nvidia-cuda-12: cuda12-trellis2cpp-development
nvidia-cuda-13: cuda13-trellis2cpp-development
nvidia-l4t: nvidia-l4t-arm64-trellis2cpp-development
nvidia-l4t-cuda-12: nvidia-l4t-arm64-trellis2cpp-development
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-trellis2cpp-development
vulkan: vulkan-trellis2cpp-development
- name: cpu-neutts
license: apache-2.0
description: |
NeuTTS Air is the world’s first super-realistic, on-device, TTS speech language model with instant voice cloning. Built off a 0.5B LLM backbone, NeuTTS Air brings natural-sounding speech, real-time performance, built-in security and speaker cloning to your local device - unlocking a new category of embedded voice agents, assistants, toys, and compliance-safe apps.
urls:
- https://github.com/neuphonic/neutts-air
tags:
- text-to-speech
- TTS
capabilities:
amd: rocm-neutts
default: cpu-neutts
nvidia: cuda12-neutts
nvidia-cuda-12: cuda12-neutts
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-neutts
mirrors:
- localai/localai-backends:latest-cpu-neutts
- name: cuda12-neutts
license: apache-2.0
description: |
NeuTTS Air is the world’s first super-realistic, on-device, TTS speech language model with instant voice cloning. Built off a 0.5B LLM backbone, NeuTTS Air brings natural-sounding speech, real-time performance, built-in security and speaker cloning to your local device - unlocking a new category of embedded voice agents, assistants, toys, and compliance-safe apps.
urls:
- https://github.com/neuphonic/neutts-air
tags:
- text-to-speech
- TTS
capabilities:
amd: rocm-neutts
default: cpu-neutts
nvidia: cuda12-neutts
nvidia-cuda-12: cuda12-neutts
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-neutts
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-12-neutts
- name: rocm-neutts
license: apache-2.0
description: |
NeuTTS Air is the world’s first super-realistic, on-device, TTS speech language model with instant voice cloning. Built off a 0.5B LLM backbone, NeuTTS Air brings natural-sounding speech, real-time performance, built-in security and speaker cloning to your local device - unlocking a new category of embedded voice agents, assistants, toys, and compliance-safe apps.
urls:
- https://github.com/neuphonic/neutts-air
tags:
- text-to-speech
- TTS
capabilities:
amd: rocm-neutts
default: cpu-neutts
nvidia: cuda12-neutts
nvidia-cuda-12: cuda12-neutts
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-neutts
mirrors:
- localai/localai-backends:latest-gpu-rocm-hipblas-neutts
- name: cpu-neutts-development
license: apache-2.0
description: |
NeuTTS Air is the world’s first super-realistic, on-device, TTS speech language model with instant voice cloning. Built off a 0.5B LLM backbone, NeuTTS Air brings natural-sounding speech, real-time performance, built-in security and speaker cloning to your local device - unlocking a new category of embedded voice agents, assistants, toys, and compliance-safe apps.
urls:
- https://github.com/neuphonic/neutts-air
tags:
- text-to-speech
- TTS
capabilities:
amd: rocm-neutts
default: cpu-neutts
nvidia: cuda12-neutts
nvidia-cuda-12: cuda12-neutts
uri: quay.io/go-skynet/local-ai-backends:master-cpu-neutts
mirrors:
- localai/localai-backends:master-cpu-neutts
- name: cuda12-neutts-development
license: apache-2.0
description: |
NeuTTS Air is the world’s first super-realistic, on-device, TTS speech language model with instant voice cloning. Built off a 0.5B LLM backbone, NeuTTS Air brings natural-sounding speech, real-time performance, built-in security and speaker cloning to your local device - unlocking a new category of embedded voice agents, assistants, toys, and compliance-safe apps.
urls:
- https://github.com/neuphonic/neutts-air
tags:
- text-to-speech
- TTS
capabilities:
amd: rocm-neutts
default: cpu-neutts
nvidia: cuda12-neutts
nvidia-cuda-12: cuda12-neutts
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-neutts
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-12-neutts
- name: rocm-neutts-development
license: apache-2.0
description: |
NeuTTS Air is the world’s first super-realistic, on-device, TTS speech language model with instant voice cloning. Built off a 0.5B LLM backbone, NeuTTS Air brings natural-sounding speech, real-time performance, built-in security and speaker cloning to your local device - unlocking a new category of embedded voice agents, assistants, toys, and compliance-safe apps.
urls:
- https://github.com/neuphonic/neutts-air
tags:
- text-to-speech
- TTS
capabilities:
amd: rocm-neutts
default: cpu-neutts
nvidia: cuda12-neutts
nvidia-cuda-12: cuda12-neutts
uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-neutts
mirrors:
- localai/localai-backends:master-gpu-rocm-hipblas-neutts
- name: metal-mlx
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run LLMs with MLX
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
capabilities:
default: cpu-mlx
metal: metal-mlx
nvidia: cuda12-mlx
nvidia-cuda-12: cuda12-mlx
nvidia-cuda-13: cuda13-mlx
nvidia-l4t: nvidia-l4t-mlx
nvidia-l4t-cuda-12: nvidia-l4t-mlx
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx
uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-mlx
- name: metal-mlx-video
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Generate videos with LTX-2 and converted Wan2.1/Wan2.2 checkpoints using
MLX on Apple Silicon.
urls:
- https://github.com/Blaizzy/mlx-video
tags:
- text-to-video
- image-to-video
- MLX
capabilities:
metal: metal-mlx-video
uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx-video
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-mlx-video
- name: metal-mlx-video-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Generate videos with LTX-2 and converted Wan2.1/Wan2.2 checkpoints using
MLX on Apple Silicon.
urls:
- https://github.com/Blaizzy/mlx-video
tags:
- text-to-video
- image-to-video
- MLX
capabilities:
metal: metal-mlx-video
uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-mlx-video
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-mlx-video
- name: mlx-video-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Generate videos with LTX-2 and converted Wan2.1/Wan2.2 checkpoints using
MLX on Apple Silicon.
urls:
- https://github.com/Blaizzy/mlx-video
tags:
- text-to-video
- image-to-video
- MLX
capabilities:
metal: metal-mlx-video-development
- name: metal-mlx-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run LLMs with MLX
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
capabilities:
default: cpu-mlx
metal: metal-mlx
nvidia: cuda12-mlx
nvidia-cuda-12: cuda12-mlx
nvidia-cuda-13: cuda13-mlx
nvidia-l4t: nvidia-l4t-mlx
nvidia-l4t-cuda-12: nvidia-l4t-mlx
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx
uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-mlx
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-mlx
- name: mlx-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run LLMs with MLX
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
capabilities:
default: cpu-mlx-development
metal: metal-mlx-development
nvidia: cuda12-mlx-development
nvidia-cuda-12: cuda12-mlx-development
nvidia-cuda-13: cuda13-mlx-development
nvidia-l4t: nvidia-l4t-mlx-development
nvidia-l4t-cuda-12: nvidia-l4t-mlx-development
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-development
- name: metal-mlx-vlm
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Vision-Language Models with MLX
urls:
- https://github.com/Blaizzy/mlx-vlm
tags:
- text-to-text
- multimodal
- vision-language
- LLM
- MLX
capabilities:
default: cpu-mlx-vlm
metal: metal-mlx-vlm
nvidia: cuda12-mlx-vlm
nvidia-cuda-12: cuda12-mlx-vlm
nvidia-cuda-13: cuda13-mlx-vlm
nvidia-l4t: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm
uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx-vlm
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-mlx-vlm
- name: metal-mlx-vlm-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Vision-Language Models with MLX
urls:
- https://github.com/Blaizzy/mlx-vlm
tags:
- text-to-text
- multimodal
- vision-language
- LLM
- MLX
capabilities:
default: cpu-mlx-vlm
metal: metal-mlx-vlm
nvidia: cuda12-mlx-vlm
nvidia-cuda-12: cuda12-mlx-vlm
nvidia-cuda-13: cuda13-mlx-vlm
nvidia-l4t: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm
uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-mlx-vlm
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-mlx-vlm
- name: mlx-vlm-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Vision-Language Models with MLX
urls:
- https://github.com/Blaizzy/mlx-vlm
tags:
- text-to-text
- multimodal
- vision-language
- LLM
- MLX
capabilities:
default: cpu-mlx-vlm-development
metal: metal-mlx-vlm-development
nvidia: cuda12-mlx-vlm-development
nvidia-cuda-12: cuda12-mlx-vlm-development
nvidia-cuda-13: cuda13-mlx-vlm-development
nvidia-l4t: nvidia-l4t-mlx-vlm-development
nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm-development
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm-development
- name: metal-mlx-audio
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Audio Models with MLX
urls:
- https://github.com/Blaizzy/mlx-audio
tags:
- audio-to-text
- audio-generation
- text-to-audio
- LLM
- MLX
capabilities:
default: cpu-mlx-audio
metal: metal-mlx-audio
nvidia: cuda12-mlx-audio
nvidia-cuda-12: cuda12-mlx-audio
nvidia-cuda-13: cuda13-mlx-audio
nvidia-l4t: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio
uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx-audio
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-mlx-audio
- name: metal-mlx-audio-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Audio Models with MLX
urls:
- https://github.com/Blaizzy/mlx-audio
tags:
- audio-to-text
- audio-generation
- text-to-audio
- LLM
- MLX
capabilities:
default: cpu-mlx-audio
metal: metal-mlx-audio
nvidia: cuda12-mlx-audio
nvidia-cuda-12: cuda12-mlx-audio
nvidia-cuda-13: cuda13-mlx-audio
nvidia-l4t: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio
uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-mlx-audio
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-mlx-audio
- name: mlx-audio-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Audio Models with MLX
urls:
- https://github.com/Blaizzy/mlx-audio
tags:
- audio-to-text
- audio-generation
- text-to-audio
- LLM
- MLX
capabilities:
default: cpu-mlx-audio-development
metal: metal-mlx-audio-development
nvidia: cuda12-mlx-audio-development
nvidia-cuda-12: cuda12-mlx-audio-development
nvidia-cuda-13: cuda13-mlx-audio-development
nvidia-l4t: nvidia-l4t-mlx-audio-development
nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio-development
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio-development
- name: metal-mlx-distributed
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run distributed LLM inference with MLX across multiple Apple Silicon Macs
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
- distributed
capabilities:
default: cpu-mlx-distributed
metal: metal-mlx-distributed
nvidia: cuda12-mlx-distributed
nvidia-cuda-12: cuda12-mlx-distributed
nvidia-cuda-13: cuda13-mlx-distributed
nvidia-l4t: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed
uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx-distributed
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-mlx-distributed
- name: metal-mlx-distributed-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run distributed LLM inference with MLX across multiple Apple Silicon Macs
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
- distributed
capabilities:
default: cpu-mlx-distributed
metal: metal-mlx-distributed
nvidia: cuda12-mlx-distributed
nvidia-cuda-12: cuda12-mlx-distributed
nvidia-cuda-13: cuda13-mlx-distributed
nvidia-l4t: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed
uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-mlx-distributed
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-mlx-distributed
- name: mlx-distributed-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run distributed LLM inference with MLX across multiple Apple Silicon Macs
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
- distributed
capabilities:
default: cpu-mlx-distributed-development
metal: metal-mlx-distributed-development
nvidia: cuda12-mlx-distributed-development
nvidia-cuda-12: cuda12-mlx-distributed-development
nvidia-cuda-13: cuda13-mlx-distributed-development
nvidia-l4t: nvidia-l4t-mlx-distributed-development
nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed-development
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed-development
- name: cpu-mlx
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run LLMs with MLX
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
capabilities:
default: cpu-mlx
metal: metal-mlx
nvidia: cuda12-mlx
nvidia-cuda-12: cuda12-mlx
nvidia-cuda-13: cuda13-mlx
nvidia-l4t: nvidia-l4t-mlx
nvidia-l4t-cuda-12: nvidia-l4t-mlx
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-mlx
mirrors:
- localai/localai-backends:latest-cpu-mlx
- name: cpu-mlx-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run LLMs with MLX
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
capabilities:
default: cpu-mlx
metal: metal-mlx
nvidia: cuda12-mlx
nvidia-cuda-12: cuda12-mlx
nvidia-cuda-13: cuda13-mlx
nvidia-l4t: nvidia-l4t-mlx
nvidia-l4t-cuda-12: nvidia-l4t-mlx
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx
uri: quay.io/go-skynet/local-ai-backends:master-cpu-mlx
mirrors:
- localai/localai-backends:master-cpu-mlx
- name: cuda12-mlx
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run LLMs with MLX
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
capabilities:
default: cpu-mlx
metal: metal-mlx
nvidia: cuda12-mlx
nvidia-cuda-12: cuda12-mlx
nvidia-cuda-13: cuda13-mlx
nvidia-l4t: nvidia-l4t-mlx
nvidia-l4t-cuda-12: nvidia-l4t-mlx
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-mlx
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-12-mlx
- name: cuda12-mlx-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run LLMs with MLX
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
capabilities:
default: cpu-mlx
metal: metal-mlx
nvidia: cuda12-mlx
nvidia-cuda-12: cuda12-mlx
nvidia-cuda-13: cuda13-mlx
nvidia-l4t: nvidia-l4t-mlx
nvidia-l4t-cuda-12: nvidia-l4t-mlx
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-mlx
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-12-mlx
- name: cuda13-mlx
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run LLMs with MLX
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
capabilities:
default: cpu-mlx
metal: metal-mlx
nvidia: cuda12-mlx
nvidia-cuda-12: cuda12-mlx
nvidia-cuda-13: cuda13-mlx
nvidia-l4t: nvidia-l4t-mlx
nvidia-l4t-cuda-12: nvidia-l4t-mlx
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-mlx
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-13-mlx
- name: cuda13-mlx-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run LLMs with MLX
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
capabilities:
default: cpu-mlx
metal: metal-mlx
nvidia: cuda12-mlx
nvidia-cuda-12: cuda12-mlx
nvidia-cuda-13: cuda13-mlx
nvidia-l4t: nvidia-l4t-mlx
nvidia-l4t-cuda-12: nvidia-l4t-mlx
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-mlx
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-13-mlx
- name: nvidia-l4t-mlx
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run LLMs with MLX
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
capabilities:
default: cpu-mlx
metal: metal-mlx
nvidia: cuda12-mlx
nvidia-cuda-12: cuda12-mlx
nvidia-cuda-13: cuda13-mlx
nvidia-l4t: nvidia-l4t-mlx
nvidia-l4t-cuda-12: nvidia-l4t-mlx
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-mlx
mirrors:
- localai/localai-backends:latest-nvidia-l4t-mlx
- name: nvidia-l4t-mlx-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run LLMs with MLX
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
capabilities:
default: cpu-mlx
metal: metal-mlx
nvidia: cuda12-mlx
nvidia-cuda-12: cuda12-mlx
nvidia-cuda-13: cuda13-mlx
nvidia-l4t: nvidia-l4t-mlx
nvidia-l4t-cuda-12: nvidia-l4t-mlx
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-mlx
mirrors:
- localai/localai-backends:master-nvidia-l4t-mlx
- name: cuda13-nvidia-l4t-arm64-mlx
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run LLMs with MLX
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
capabilities:
default: cpu-mlx
metal: metal-mlx
nvidia: cuda12-mlx
nvidia-cuda-12: cuda12-mlx
nvidia-cuda-13: cuda13-mlx
nvidia-l4t: nvidia-l4t-mlx
nvidia-l4t-cuda-12: nvidia-l4t-mlx
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx
mirrors:
- localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx
- name: cuda13-nvidia-l4t-arm64-mlx-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run LLMs with MLX
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
capabilities:
default: cpu-mlx
metal: metal-mlx
nvidia: cuda12-mlx
nvidia-cuda-12: cuda12-mlx
nvidia-cuda-13: cuda13-mlx
nvidia-l4t: nvidia-l4t-mlx
nvidia-l4t-cuda-12: nvidia-l4t-mlx
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-mlx
mirrors:
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-mlx
- name: cpu-mlx-vlm
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Vision-Language Models with MLX
urls:
- https://github.com/Blaizzy/mlx-vlm
tags:
- text-to-text
- multimodal
- vision-language
- LLM
- MLX
capabilities:
default: cpu-mlx-vlm
metal: metal-mlx-vlm
nvidia: cuda12-mlx-vlm
nvidia-cuda-12: cuda12-mlx-vlm
nvidia-cuda-13: cuda13-mlx-vlm
nvidia-l4t: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-mlx-vlm
mirrors:
- localai/localai-backends:latest-cpu-mlx-vlm
- name: cpu-mlx-vlm-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Vision-Language Models with MLX
urls:
- https://github.com/Blaizzy/mlx-vlm
tags:
- text-to-text
- multimodal
- vision-language
- LLM
- MLX
capabilities:
default: cpu-mlx-vlm
metal: metal-mlx-vlm
nvidia: cuda12-mlx-vlm
nvidia-cuda-12: cuda12-mlx-vlm
nvidia-cuda-13: cuda13-mlx-vlm
nvidia-l4t: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm
uri: quay.io/go-skynet/local-ai-backends:master-cpu-mlx-vlm
mirrors:
- localai/localai-backends:master-cpu-mlx-vlm
- name: cuda12-mlx-vlm
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Vision-Language Models with MLX
urls:
- https://github.com/Blaizzy/mlx-vlm
tags:
- text-to-text
- multimodal
- vision-language
- LLM
- MLX
capabilities:
default: cpu-mlx-vlm
metal: metal-mlx-vlm
nvidia: cuda12-mlx-vlm
nvidia-cuda-12: cuda12-mlx-vlm
nvidia-cuda-13: cuda13-mlx-vlm
nvidia-l4t: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-mlx-vlm
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-12-mlx-vlm
- name: cuda12-mlx-vlm-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Vision-Language Models with MLX
urls:
- https://github.com/Blaizzy/mlx-vlm
tags:
- text-to-text
- multimodal
- vision-language
- LLM
- MLX
capabilities:
default: cpu-mlx-vlm
metal: metal-mlx-vlm
nvidia: cuda12-mlx-vlm
nvidia-cuda-12: cuda12-mlx-vlm
nvidia-cuda-13: cuda13-mlx-vlm
nvidia-l4t: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-mlx-vlm
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-12-mlx-vlm
- name: cuda13-mlx-vlm
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Vision-Language Models with MLX
urls:
- https://github.com/Blaizzy/mlx-vlm
tags:
- text-to-text
- multimodal
- vision-language
- LLM
- MLX
capabilities:
default: cpu-mlx-vlm
metal: metal-mlx-vlm
nvidia: cuda12-mlx-vlm
nvidia-cuda-12: cuda12-mlx-vlm
nvidia-cuda-13: cuda13-mlx-vlm
nvidia-l4t: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-mlx-vlm
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-13-mlx-vlm
- name: cuda13-mlx-vlm-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Vision-Language Models with MLX
urls:
- https://github.com/Blaizzy/mlx-vlm
tags:
- text-to-text
- multimodal
- vision-language
- LLM
- MLX
capabilities:
default: cpu-mlx-vlm
metal: metal-mlx-vlm
nvidia: cuda12-mlx-vlm
nvidia-cuda-12: cuda12-mlx-vlm
nvidia-cuda-13: cuda13-mlx-vlm
nvidia-l4t: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-mlx-vlm
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-13-mlx-vlm
- name: nvidia-l4t-mlx-vlm
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Vision-Language Models with MLX
urls:
- https://github.com/Blaizzy/mlx-vlm
tags:
- text-to-text
- multimodal
- vision-language
- LLM
- MLX
capabilities:
default: cpu-mlx-vlm
metal: metal-mlx-vlm
nvidia: cuda12-mlx-vlm
nvidia-cuda-12: cuda12-mlx-vlm
nvidia-cuda-13: cuda13-mlx-vlm
nvidia-l4t: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-mlx-vlm
mirrors:
- localai/localai-backends:latest-nvidia-l4t-mlx-vlm
- name: nvidia-l4t-mlx-vlm-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Vision-Language Models with MLX
urls:
- https://github.com/Blaizzy/mlx-vlm
tags:
- text-to-text
- multimodal
- vision-language
- LLM
- MLX
capabilities:
default: cpu-mlx-vlm
metal: metal-mlx-vlm
nvidia: cuda12-mlx-vlm
nvidia-cuda-12: cuda12-mlx-vlm
nvidia-cuda-13: cuda13-mlx-vlm
nvidia-l4t: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-mlx-vlm
mirrors:
- localai/localai-backends:master-nvidia-l4t-mlx-vlm
- name: cuda13-nvidia-l4t-arm64-mlx-vlm
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Vision-Language Models with MLX
urls:
- https://github.com/Blaizzy/mlx-vlm
tags:
- text-to-text
- multimodal
- vision-language
- LLM
- MLX
capabilities:
default: cpu-mlx-vlm
metal: metal-mlx-vlm
nvidia: cuda12-mlx-vlm
nvidia-cuda-12: cuda12-mlx-vlm
nvidia-cuda-13: cuda13-mlx-vlm
nvidia-l4t: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-vlm
mirrors:
- localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-vlm
- name: cuda13-nvidia-l4t-arm64-mlx-vlm-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Vision-Language Models with MLX
urls:
- https://github.com/Blaizzy/mlx-vlm
tags:
- text-to-text
- multimodal
- vision-language
- LLM
- MLX
capabilities:
default: cpu-mlx-vlm
metal: metal-mlx-vlm
nvidia: cuda12-mlx-vlm
nvidia-cuda-12: cuda12-mlx-vlm
nvidia-cuda-13: cuda13-mlx-vlm
nvidia-l4t: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-vlm
mirrors:
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-vlm
- name: cpu-mlx-audio
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Audio Models with MLX
urls:
- https://github.com/Blaizzy/mlx-audio
tags:
- audio-to-text
- audio-generation
- text-to-audio
- LLM
- MLX
capabilities:
default: cpu-mlx-audio
metal: metal-mlx-audio
nvidia: cuda12-mlx-audio
nvidia-cuda-12: cuda12-mlx-audio
nvidia-cuda-13: cuda13-mlx-audio
nvidia-l4t: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-mlx-audio
mirrors:
- localai/localai-backends:latest-cpu-mlx-audio
- name: cpu-mlx-audio-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Audio Models with MLX
urls:
- https://github.com/Blaizzy/mlx-audio
tags:
- audio-to-text
- audio-generation
- text-to-audio
- LLM
- MLX
capabilities:
default: cpu-mlx-audio
metal: metal-mlx-audio
nvidia: cuda12-mlx-audio
nvidia-cuda-12: cuda12-mlx-audio
nvidia-cuda-13: cuda13-mlx-audio
nvidia-l4t: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio
uri: quay.io/go-skynet/local-ai-backends:master-cpu-mlx-audio
mirrors:
- localai/localai-backends:master-cpu-mlx-audio
- name: cuda12-mlx-audio
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Audio Models with MLX
urls:
- https://github.com/Blaizzy/mlx-audio
tags:
- audio-to-text
- audio-generation
- text-to-audio
- LLM
- MLX
capabilities:
default: cpu-mlx-audio
metal: metal-mlx-audio
nvidia: cuda12-mlx-audio
nvidia-cuda-12: cuda12-mlx-audio
nvidia-cuda-13: cuda13-mlx-audio
nvidia-l4t: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-mlx-audio
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-12-mlx-audio
- name: cuda12-mlx-audio-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Audio Models with MLX
urls:
- https://github.com/Blaizzy/mlx-audio
tags:
- audio-to-text
- audio-generation
- text-to-audio
- LLM
- MLX
capabilities:
default: cpu-mlx-audio
metal: metal-mlx-audio
nvidia: cuda12-mlx-audio
nvidia-cuda-12: cuda12-mlx-audio
nvidia-cuda-13: cuda13-mlx-audio
nvidia-l4t: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-mlx-audio
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-12-mlx-audio
- name: cuda13-mlx-audio
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Audio Models with MLX
urls:
- https://github.com/Blaizzy/mlx-audio
tags:
- audio-to-text
- audio-generation
- text-to-audio
- LLM
- MLX
capabilities:
default: cpu-mlx-audio
metal: metal-mlx-audio
nvidia: cuda12-mlx-audio
nvidia-cuda-12: cuda12-mlx-audio
nvidia-cuda-13: cuda13-mlx-audio
nvidia-l4t: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-mlx-audio
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-13-mlx-audio
- name: cuda13-mlx-audio-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Audio Models with MLX
urls:
- https://github.com/Blaizzy/mlx-audio
tags:
- audio-to-text
- audio-generation
- text-to-audio
- LLM
- MLX
capabilities:
default: cpu-mlx-audio
metal: metal-mlx-audio
nvidia: cuda12-mlx-audio
nvidia-cuda-12: cuda12-mlx-audio
nvidia-cuda-13: cuda13-mlx-audio
nvidia-l4t: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-mlx-audio
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-13-mlx-audio
- name: nvidia-l4t-mlx-audio
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Audio Models with MLX
urls:
- https://github.com/Blaizzy/mlx-audio
tags:
- audio-to-text
- audio-generation
- text-to-audio
- LLM
- MLX
capabilities:
default: cpu-mlx-audio
metal: metal-mlx-audio
nvidia: cuda12-mlx-audio
nvidia-cuda-12: cuda12-mlx-audio
nvidia-cuda-13: cuda13-mlx-audio
nvidia-l4t: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-mlx-audio
mirrors:
- localai/localai-backends:latest-nvidia-l4t-mlx-audio
- name: nvidia-l4t-mlx-audio-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Audio Models with MLX
urls:
- https://github.com/Blaizzy/mlx-audio
tags:
- audio-to-text
- audio-generation
- text-to-audio
- LLM
- MLX
capabilities:
default: cpu-mlx-audio
metal: metal-mlx-audio
nvidia: cuda12-mlx-audio
nvidia-cuda-12: cuda12-mlx-audio
nvidia-cuda-13: cuda13-mlx-audio
nvidia-l4t: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-mlx-audio
mirrors:
- localai/localai-backends:master-nvidia-l4t-mlx-audio
- name: cuda13-nvidia-l4t-arm64-mlx-audio
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Audio Models with MLX
urls:
- https://github.com/Blaizzy/mlx-audio
tags:
- audio-to-text
- audio-generation
- text-to-audio
- LLM
- MLX
capabilities:
default: cpu-mlx-audio
metal: metal-mlx-audio
nvidia: cuda12-mlx-audio
nvidia-cuda-12: cuda12-mlx-audio
nvidia-cuda-13: cuda13-mlx-audio
nvidia-l4t: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-audio
mirrors:
- localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-audio
- name: cuda13-nvidia-l4t-arm64-mlx-audio-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run Audio Models with MLX
urls:
- https://github.com/Blaizzy/mlx-audio
tags:
- audio-to-text
- audio-generation
- text-to-audio
- LLM
- MLX
capabilities:
default: cpu-mlx-audio
metal: metal-mlx-audio
nvidia: cuda12-mlx-audio
nvidia-cuda-12: cuda12-mlx-audio
nvidia-cuda-13: cuda13-mlx-audio
nvidia-l4t: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-audio
mirrors:
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-audio
- name: cpu-mlx-distributed
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run distributed LLM inference with MLX across multiple Apple Silicon Macs
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
- distributed
capabilities:
default: cpu-mlx-distributed
metal: metal-mlx-distributed
nvidia: cuda12-mlx-distributed
nvidia-cuda-12: cuda12-mlx-distributed
nvidia-cuda-13: cuda13-mlx-distributed
nvidia-l4t: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-mlx-distributed
mirrors:
- localai/localai-backends:latest-cpu-mlx-distributed
- name: cpu-mlx-distributed-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run distributed LLM inference with MLX across multiple Apple Silicon Macs
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
- distributed
capabilities:
default: cpu-mlx-distributed
metal: metal-mlx-distributed
nvidia: cuda12-mlx-distributed
nvidia-cuda-12: cuda12-mlx-distributed
nvidia-cuda-13: cuda13-mlx-distributed
nvidia-l4t: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed
uri: quay.io/go-skynet/local-ai-backends:master-cpu-mlx-distributed
mirrors:
- localai/localai-backends:master-cpu-mlx-distributed
- name: cuda12-mlx-distributed
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run distributed LLM inference with MLX across multiple Apple Silicon Macs
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
- distributed
capabilities:
default: cpu-mlx-distributed
metal: metal-mlx-distributed
nvidia: cuda12-mlx-distributed
nvidia-cuda-12: cuda12-mlx-distributed
nvidia-cuda-13: cuda13-mlx-distributed
nvidia-l4t: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-mlx-distributed
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-12-mlx-distributed
- name: cuda12-mlx-distributed-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run distributed LLM inference with MLX across multiple Apple Silicon Macs
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
- distributed
capabilities:
default: cpu-mlx-distributed
metal: metal-mlx-distributed
nvidia: cuda12-mlx-distributed
nvidia-cuda-12: cuda12-mlx-distributed
nvidia-cuda-13: cuda13-mlx-distributed
nvidia-l4t: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-mlx-distributed
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-12-mlx-distributed
- name: cuda13-mlx-distributed
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run distributed LLM inference with MLX across multiple Apple Silicon Macs
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
- distributed
capabilities:
default: cpu-mlx-distributed
metal: metal-mlx-distributed
nvidia: cuda12-mlx-distributed
nvidia-cuda-12: cuda12-mlx-distributed
nvidia-cuda-13: cuda13-mlx-distributed
nvidia-l4t: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-mlx-distributed
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-13-mlx-distributed
- name: cuda13-mlx-distributed-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run distributed LLM inference with MLX across multiple Apple Silicon Macs
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
- distributed
capabilities:
default: cpu-mlx-distributed
metal: metal-mlx-distributed
nvidia: cuda12-mlx-distributed
nvidia-cuda-12: cuda12-mlx-distributed
nvidia-cuda-13: cuda13-mlx-distributed
nvidia-l4t: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-mlx-distributed
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-13-mlx-distributed
- name: nvidia-l4t-mlx-distributed
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run distributed LLM inference with MLX across multiple Apple Silicon Macs
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
- distributed
capabilities:
default: cpu-mlx-distributed
metal: metal-mlx-distributed
nvidia: cuda12-mlx-distributed
nvidia-cuda-12: cuda12-mlx-distributed
nvidia-cuda-13: cuda13-mlx-distributed
nvidia-l4t: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-mlx-distributed
mirrors:
- localai/localai-backends:latest-nvidia-l4t-mlx-distributed
- name: nvidia-l4t-mlx-distributed-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run distributed LLM inference with MLX across multiple Apple Silicon Macs
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
- distributed
capabilities:
default: cpu-mlx-distributed
metal: metal-mlx-distributed
nvidia: cuda12-mlx-distributed
nvidia-cuda-12: cuda12-mlx-distributed
nvidia-cuda-13: cuda13-mlx-distributed
nvidia-l4t: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-mlx-distributed
mirrors:
- localai/localai-backends:master-nvidia-l4t-mlx-distributed
- name: cuda13-nvidia-l4t-arm64-mlx-distributed
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run distributed LLM inference with MLX across multiple Apple Silicon Macs
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
- distributed
capabilities:
default: cpu-mlx-distributed
metal: metal-mlx-distributed
nvidia: cuda12-mlx-distributed
nvidia-cuda-12: cuda12-mlx-distributed
nvidia-cuda-13: cuda13-mlx-distributed
nvidia-l4t: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-distributed
mirrors:
- localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-distributed
- name: cuda13-nvidia-l4t-arm64-mlx-distributed-development
license: MIT
icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
description: |
Run distributed LLM inference with MLX across multiple Apple Silicon Macs
urls:
- https://github.com/ml-explore/mlx-lm
tags:
- text-to-text
- LLM
- MLX
- distributed
capabilities:
default: cpu-mlx-distributed
metal: metal-mlx-distributed
nvidia: cuda12-mlx-distributed
nvidia-cuda-12: cuda12-mlx-distributed
nvidia-cuda-13: cuda13-mlx-distributed
nvidia-l4t: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-distributed
mirrors:
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-distributed
- name: cpu-kitten-tts
license: apache-2.0
description: |
Kitten TTS is a text-to-speech model that can generate speech from text.
urls:
- https://github.com/KittenML/KittenTTS
tags:
- text-to-speech
- TTS
capabilities:
default: cpu-kitten-tts
metal: metal-kitten-tts
uri: quay.io/go-skynet/local-ai-backends:latest-kitten-tts
mirrors:
- localai/localai-backends:latest-kitten-tts
- name: cpu-kitten-tts-development
license: apache-2.0
description: |
Kitten TTS is a text-to-speech model that can generate speech from text.
urls:
- https://github.com/KittenML/KittenTTS
tags:
- text-to-speech
- TTS
capabilities:
default: cpu-kitten-tts
metal: metal-kitten-tts
uri: quay.io/go-skynet/local-ai-backends:master-kitten-tts
mirrors:
- localai/localai-backends:master-kitten-tts
- name: kitten-tts-development
license: apache-2.0
description: |
Kitten TTS is a text-to-speech model that can generate speech from text.
urls:
- https://github.com/KittenML/KittenTTS
tags:
- text-to-speech
- TTS
capabilities:
default: cpu-kitten-tts-development
metal: metal-kitten-tts-development
- name: metal-kitten-tts
license: apache-2.0
description: |
Kitten TTS is a text-to-speech model that can generate speech from text.
urls:
- https://github.com/KittenML/KittenTTS
tags:
- text-to-speech
- TTS
capabilities:
default: cpu-kitten-tts
metal: metal-kitten-tts
uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-kitten-tts
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-kitten-tts
- name: metal-kitten-tts-development
license: apache-2.0
description: |
Kitten TTS is a text-to-speech model that can generate speech from text.
urls:
- https://github.com/KittenML/KittenTTS
tags:
- text-to-speech
- TTS
capabilities:
default: cpu-kitten-tts
metal: metal-kitten-tts
uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-kitten-tts
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-kitten-tts
- name: cpu-local-store
alias: local-store
license: MIT
description: |
Local Store is a local-first, self-hosted, and open-source vector database.
urls:
- https://github.com/mudler/LocalAI
tags:
- vector-database
- local-first
- open-source
- CPU
capabilities:
default: cpu-local-store
metal: metal-local-store
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-local-store
mirrors:
- localai/localai-backends:latest-cpu-local-store
- name: cpu-local-store-development
alias: local-store
license: MIT
description: |
Local Store is a local-first, self-hosted, and open-source vector database.
urls:
- https://github.com/mudler/LocalAI
tags:
- vector-database
- local-first
- open-source
- CPU
capabilities:
default: cpu-local-store
metal: metal-local-store
uri: quay.io/go-skynet/local-ai-backends:master-cpu-local-store
mirrors:
- localai/localai-backends:master-cpu-local-store
- name: local-store-development
alias: local-store
license: MIT
description: |
Local Store is a local-first, self-hosted, and open-source vector database.
urls:
- https://github.com/mudler/LocalAI
tags:
- vector-database
- local-first
- open-source
- CPU
capabilities:
default: cpu-local-store-development
metal: metal-local-store-development
- name: metal-local-store
license: MIT
description: |
Local Store is a local-first, self-hosted, and open-source vector database.
urls:
- https://github.com/mudler/LocalAI
tags:
- vector-database
- local-first
- open-source
- CPU
capabilities:
default: cpu-local-store
metal: metal-local-store
uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-local-store
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-local-store
- name: metal-local-store-development
alias: local-store
license: MIT
description: |
Local Store is a local-first, self-hosted, and open-source vector database.
urls:
- https://github.com/mudler/LocalAI
tags:
- vector-database
- local-first
- open-source
- CPU
capabilities:
default: cpu-local-store
metal: metal-local-store
uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-local-store
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-local-store
- name: cpu-cloud-proxy
alias: cloud-proxy
license: MIT
description: |
Forward OpenAI-compatible and Anthropic chat requests to external providers.
urls:
- https://github.com/mudler/LocalAI/tree/master/backend/go/cloud-proxy
tags:
- text-to-text
- cloud
- proxy
- CPU
capabilities:
default: cpu-cloud-proxy
metal: metal-cloud-proxy
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-cloud-proxy
mirrors:
- localai/localai-backends:latest-cpu-cloud-proxy
- name: cpu-cloud-proxy-development
alias: cloud-proxy
license: MIT
description: |
Forward OpenAI-compatible and Anthropic chat requests to external providers.
urls:
- https://github.com/mudler/LocalAI/tree/master/backend/go/cloud-proxy
tags:
- text-to-text
- cloud
- proxy
- CPU
capabilities:
default: cpu-cloud-proxy
metal: metal-cloud-proxy
uri: quay.io/go-skynet/local-ai-backends:master-cpu-cloud-proxy
mirrors:
- localai/localai-backends:master-cpu-cloud-proxy
- name: cloud-proxy-development
alias: cloud-proxy
license: MIT
description: |
Forward OpenAI-compatible and Anthropic chat requests to external providers.
urls:
- https://github.com/mudler/LocalAI/tree/master/backend/go/cloud-proxy
tags:
- text-to-text
- cloud
- proxy
- CPU
capabilities:
default: cpu-cloud-proxy-development
metal: metal-cloud-proxy-development
- name: metal-cloud-proxy
alias: cloud-proxy
license: MIT
description: |
Forward OpenAI-compatible and Anthropic chat requests to external providers.
urls:
- https://github.com/mudler/LocalAI/tree/master/backend/go/cloud-proxy
tags:
- text-to-text
- cloud
- proxy
- CPU
capabilities:
default: cpu-cloud-proxy
metal: metal-cloud-proxy
uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-cloud-proxy
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-cloud-proxy
- name: metal-cloud-proxy-development
alias: cloud-proxy
license: MIT
description: |
Forward OpenAI-compatible and Anthropic chat requests to external providers.
urls:
- https://github.com/mudler/LocalAI/tree/master/backend/go/cloud-proxy
tags:
- text-to-text
- cloud
- proxy
- CPU
capabilities:
default: cpu-cloud-proxy
metal: metal-cloud-proxy
uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-cloud-proxy
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-cloud-proxy
- name: cpu-localai-proxy
alias: localai-proxy
license: MIT
description: |
Serve a model from another LocalAI instance: text, embeddings, rerank, audio, image and video requests are forwarded to its REST API.
urls:
- https://github.com/mudler/LocalAI/tree/master/backend/go/localai-proxy
tags:
- text-to-text
- proxy
- CPU
capabilities:
default: cpu-localai-proxy
metal: metal-localai-proxy
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-localai-proxy
mirrors:
- localai/localai-backends:latest-cpu-localai-proxy
- name: cpu-localai-proxy-development
alias: localai-proxy
license: MIT
description: |
Serve a model from another LocalAI instance: text, embeddings, rerank, audio, image and video requests are forwarded to its REST API.
urls:
- https://github.com/mudler/LocalAI/tree/master/backend/go/localai-proxy
tags:
- text-to-text
- proxy
- CPU
capabilities:
default: cpu-localai-proxy
metal: metal-localai-proxy
uri: quay.io/go-skynet/local-ai-backends:master-cpu-localai-proxy
mirrors:
- localai/localai-backends:master-cpu-localai-proxy
- name: localai-proxy-development
alias: localai-proxy
license: MIT
description: |
Serve a model from another LocalAI instance: text, embeddings, rerank, audio, image and video requests are forwarded to its REST API.
urls:
- https://github.com/mudler/LocalAI/tree/master/backend/go/localai-proxy
tags:
- text-to-text
- proxy
- CPU
capabilities:
default: cpu-localai-proxy-development
metal: metal-localai-proxy-development
- name: metal-localai-proxy
alias: localai-proxy
license: MIT
description: |
Serve a model from another LocalAI instance: text, embeddings, rerank, audio, image and video requests are forwarded to its REST API.
urls:
- https://github.com/mudler/LocalAI/tree/master/backend/go/localai-proxy
tags:
- text-to-text
- proxy
- CPU
capabilities:
default: cpu-localai-proxy
metal: metal-localai-proxy
uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-localai-proxy
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-localai-proxy
- name: metal-localai-proxy-development
alias: localai-proxy
license: MIT
description: |
Serve a model from another LocalAI instance: text, embeddings, rerank, audio, image and video requests are forwarded to its REST API.
urls:
- https://github.com/mudler/LocalAI/tree/master/backend/go/localai-proxy
tags:
- text-to-text
- proxy
- CPU
capabilities:
default: cpu-localai-proxy
metal: metal-localai-proxy
uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-localai-proxy
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-localai-proxy
- name: cpu-valkey-store
alias: valkey-store
license: MIT
description: |
Valkey Store is a Valkey Search (FT.*) backed vector store for LocalAI. It
persists vectors across restarts and supports opt-in HNSW indexing. Requires
a reachable Valkey Search server (valkey/valkey-bundle).
urls:
- https://github.com/mudler/LocalAI
tags:
- vector-database
- valkey
- open-source
- CPU
capabilities:
default: cpu-valkey-store
metal: metal-valkey-store
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-valkey-store
mirrors:
- localai/localai-backends:latest-cpu-valkey-store
- name: cpu-valkey-store-development
alias: valkey-store
license: MIT
description: |
Valkey Store is a Valkey Search (FT.*) backed vector store for LocalAI. It
persists vectors across restarts and supports opt-in HNSW indexing. Requires
a reachable Valkey Search server (valkey/valkey-bundle).
urls:
- https://github.com/mudler/LocalAI
tags:
- vector-database
- valkey
- open-source
- CPU
capabilities:
default: cpu-valkey-store
metal: metal-valkey-store
uri: quay.io/go-skynet/local-ai-backends:master-cpu-valkey-store
mirrors:
- localai/localai-backends:master-cpu-valkey-store
- name: valkey-store-development
alias: valkey-store
license: MIT
description: |
Valkey Store is a Valkey Search (FT.*) backed vector store for LocalAI. It
persists vectors across restarts and supports opt-in HNSW indexing. Requires
a reachable Valkey Search server (valkey/valkey-bundle).
urls:
- https://github.com/mudler/LocalAI
tags:
- vector-database
- valkey
- open-source
- CPU
capabilities:
default: cpu-valkey-store-development
metal: metal-valkey-store-development
- name: metal-valkey-store
license: MIT
description: |
Valkey Store is a Valkey Search (FT.*) backed vector store for LocalAI. It
persists vectors across restarts and supports opt-in HNSW indexing. Requires
a reachable Valkey Search server (valkey/valkey-bundle).
urls:
- https://github.com/mudler/LocalAI
tags:
- vector-database
- valkey
- open-source
- CPU
capabilities:
default: cpu-valkey-store
metal: metal-valkey-store
uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-valkey-store
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-valkey-store
- name: metal-valkey-store-development
alias: valkey-store
license: MIT
description: |
Valkey Store is a Valkey Search (FT.*) backed vector store for LocalAI. It
persists vectors across restarts and supports opt-in HNSW indexing. Requires
a reachable Valkey Search server (valkey/valkey-bundle).
urls:
- https://github.com/mudler/LocalAI
tags:
- vector-database
- valkey
- open-source
- CPU
capabilities:
default: cpu-valkey-store
metal: metal-valkey-store
uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-valkey-store
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-valkey-store
- name: cpu-qdrant-store
alias: qdrant-store
license: MIT
description: |
Qdrant Store is a Qdrant-backed vector store for LocalAI. It persists
vectors across restarts in HNSW-indexed collections and works with
self-hosted Qdrant (single node or cluster) and Qdrant Cloud. Requires a
reachable Qdrant server (gRPC port, 6334 by default).
urls:
- https://github.com/mudler/LocalAI
- https://github.com/qdrant/qdrant
tags:
- vector-database
- qdrant
- open-source
- CPU
capabilities:
default: cpu-qdrant-store
metal: metal-qdrant-store
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-qdrant-store
mirrors:
- localai/localai-backends:latest-cpu-qdrant-store
- name: cpu-qdrant-store-development
alias: qdrant-store
license: MIT
description: |
Qdrant Store is a Qdrant-backed vector store for LocalAI. It persists
vectors across restarts in HNSW-indexed collections and works with
self-hosted Qdrant (single node or cluster) and Qdrant Cloud. Requires a
reachable Qdrant server (gRPC port, 6334 by default).
urls:
- https://github.com/mudler/LocalAI
- https://github.com/qdrant/qdrant
tags:
- vector-database
- qdrant
- open-source
- CPU
capabilities:
default: cpu-qdrant-store
metal: metal-qdrant-store
uri: quay.io/go-skynet/local-ai-backends:master-cpu-qdrant-store
mirrors:
- localai/localai-backends:master-cpu-qdrant-store
- name: qdrant-store-development
alias: qdrant-store
license: MIT
description: |
Qdrant Store is a Qdrant-backed vector store for LocalAI. It persists
vectors across restarts in HNSW-indexed collections and works with
self-hosted Qdrant (single node or cluster) and Qdrant Cloud. Requires a
reachable Qdrant server (gRPC port, 6334 by default).
urls:
- https://github.com/mudler/LocalAI
- https://github.com/qdrant/qdrant
tags:
- vector-database
- qdrant
- open-source
- CPU
capabilities:
default: cpu-qdrant-store-development
metal: metal-qdrant-store-development
- name: metal-qdrant-store
license: MIT
description: |
Qdrant Store is a Qdrant-backed vector store for LocalAI. It persists
vectors across restarts in HNSW-indexed collections and works with
self-hosted Qdrant (single node or cluster) and Qdrant Cloud. Requires a
reachable Qdrant server (gRPC port, 6334 by default).
urls:
- https://github.com/mudler/LocalAI
- https://github.com/qdrant/qdrant
tags:
- vector-database
- qdrant
- open-source
- CPU
capabilities:
default: cpu-qdrant-store
metal: metal-qdrant-store
uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-qdrant-store
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-qdrant-store
- name: metal-qdrant-store-development
alias: qdrant-store
license: MIT
description: |
Qdrant Store is a Qdrant-backed vector store for LocalAI. It persists
vectors across restarts in HNSW-indexed collections and works with
self-hosted Qdrant (single node or cluster) and Qdrant Cloud. Requires a
reachable Qdrant server (gRPC port, 6334 by default).
urls:
- https://github.com/mudler/LocalAI
- https://github.com/qdrant/qdrant
tags:
- vector-database
- qdrant
- open-source
- CPU
capabilities:
default: cpu-qdrant-store
metal: metal-qdrant-store
uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-qdrant-store
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-qdrant-store
- name: cpu-opus
alias: opus
license: BSD-3-Clause
description: |
Opus audio codec backend for encoding and decoding audio.
Required for WebRTC transport in the Realtime API.
urls:
- https://opus-codec.org/
tags:
- audio-codec
- opus
- WebRTC
- realtime
capabilities:
default: cpu-opus
metal: metal-opus
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-opus
mirrors:
- localai/localai-backends:latest-cpu-opus
- name: cpu-opus-development
alias: opus
license: BSD-3-Clause
description: |
Opus audio codec backend for encoding and decoding audio.
Required for WebRTC transport in the Realtime API.
urls:
- https://opus-codec.org/
tags:
- audio-codec
- opus
- WebRTC
- realtime
capabilities:
default: cpu-opus
metal: metal-opus
uri: quay.io/go-skynet/local-ai-backends:master-cpu-opus
mirrors:
- localai/localai-backends:master-cpu-opus
- name: metal-opus
alias: opus
license: BSD-3-Clause
description: |
Opus audio codec backend for encoding and decoding audio.
Required for WebRTC transport in the Realtime API.
urls:
- https://opus-codec.org/
tags:
- audio-codec
- opus
- WebRTC
- realtime
capabilities:
default: cpu-opus
metal: metal-opus
uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-opus
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-opus
- name: metal-opus-development
alias: opus
license: BSD-3-Clause
description: |
Opus audio codec backend for encoding and decoding audio.
Required for WebRTC transport in the Realtime API.
urls:
- https://opus-codec.org/
tags:
- audio-codec
- opus
- WebRTC
- realtime
capabilities:
default: cpu-opus
metal: metal-opus
uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-opus
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-opus
- name: cpu-silero-vad
icon: https://user-images.githubusercontent.com/12515440/89997349-b3523080-dc94-11ea-9906-ca2e8bc50535.png
description: |
Silero VAD: pre-trained enterprise-grade Voice Activity Detector.
Silero VAD is a voice activity detection model that can be used to detect whether a given audio contains speech or not.
urls:
- https://github.com/snakers4/silero-vad
tags:
- voice-activity-detection
- VAD
- silero-vad
- CPU
capabilities:
default: cpu-silero-vad
metal: metal-silero-vad
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-silero-vad
mirrors:
- localai/localai-backends:latest-cpu-silero-vad
- name: cpu-silero-vad-development
icon: https://user-images.githubusercontent.com/12515440/89997349-b3523080-dc94-11ea-9906-ca2e8bc50535.png
description: |
Silero VAD: pre-trained enterprise-grade Voice Activity Detector.
Silero VAD is a voice activity detection model that can be used to detect whether a given audio contains speech or not.
urls:
- https://github.com/snakers4/silero-vad
tags:
- voice-activity-detection
- VAD
- silero-vad
- CPU
capabilities:
default: cpu-silero-vad
metal: metal-silero-vad
uri: quay.io/go-skynet/local-ai-backends:master-cpu-silero-vad
mirrors:
- localai/localai-backends:master-cpu-silero-vad
- name: silero-vad-development
icon: https://user-images.githubusercontent.com/12515440/89997349-b3523080-dc94-11ea-9906-ca2e8bc50535.png
description: |
Silero VAD: pre-trained enterprise-grade Voice Activity Detector.
Silero VAD is a voice activity detection model that can be used to detect whether a given audio contains speech or not.
urls:
- https://github.com/snakers4/silero-vad
tags:
- voice-activity-detection
- VAD
- silero-vad
- CPU
capabilities:
default: cpu-silero-vad-development
metal: metal-silero-vad-development
- name: metal-silero-vad
icon: https://user-images.githubusercontent.com/12515440/89997349-b3523080-dc94-11ea-9906-ca2e8bc50535.png
description: |
Silero VAD: pre-trained enterprise-grade Voice Activity Detector.
Silero VAD is a voice activity detection model that can be used to detect whether a given audio contains speech or not.
urls:
- https://github.com/snakers4/silero-vad
tags:
- voice-activity-detection
- VAD
- silero-vad
- CPU
capabilities:
default: cpu-silero-vad
metal: metal-silero-vad
uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-silero-vad
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-silero-vad
- name: metal-silero-vad-development
icon: https://user-images.githubusercontent.com/12515440/89997349-b3523080-dc94-11ea-9906-ca2e8bc50535.png
description: |
Silero VAD: pre-trained enterprise-grade Voice Activity Detector.
Silero VAD is a voice activity detection model that can be used to detect whether a given audio contains speech or not.
urls:
- https://github.com/snakers4/silero-vad
tags:
- voice-activity-detection
- VAD
- silero-vad
- CPU
capabilities:
default: cpu-silero-vad
metal: metal-silero-vad
uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-silero-vad
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-silero-vad
- name: cpu-piper
license: MIT
icon: https://github.com/OHF-Voice/piper1-gpl/raw/main/etc/logo.png
description: |
A fast, local neural text to speech system
urls:
- https://github.com/rhasspy/piper
- https://github.com/mudler/go-piper
tags:
- text-to-speech
- TTS
capabilities:
default: cpu-piper
metal: metal-piper
uri: quay.io/go-skynet/local-ai-backends:latest-piper
mirrors:
- localai/localai-backends:latest-piper
- name: cpu-piper-development
license: MIT
icon: https://github.com/OHF-Voice/piper1-gpl/raw/main/etc/logo.png
description: |
A fast, local neural text to speech system
urls:
- https://github.com/rhasspy/piper
- https://github.com/mudler/go-piper
tags:
- text-to-speech
- TTS
capabilities:
default: cpu-piper
metal: metal-piper
uri: quay.io/go-skynet/local-ai-backends:master-piper
mirrors:
- localai/localai-backends:master-piper
- name: piper-development
license: MIT
icon: https://github.com/OHF-Voice/piper1-gpl/raw/main/etc/logo.png
description: |
A fast, local neural text to speech system
urls:
- https://github.com/rhasspy/piper
- https://github.com/mudler/go-piper
tags:
- text-to-speech
- TTS
capabilities:
default: cpu-piper-development
metal: metal-piper-development
- name: metal-piper
license: MIT
icon: https://github.com/OHF-Voice/piper1-gpl/raw/main/etc/logo.png
description: |
A fast, local neural text to speech system
urls:
- https://github.com/rhasspy/piper
- https://github.com/mudler/go-piper
tags:
- text-to-speech
- TTS
capabilities:
default: cpu-piper
metal: metal-piper
uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-piper
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-piper
- name: metal-piper-development
license: MIT
icon: https://github.com/OHF-Voice/piper1-gpl/raw/main/etc/logo.png
description: |
A fast, local neural text to speech system
urls:
- https://github.com/rhasspy/piper
- https://github.com/mudler/go-piper
tags:
- text-to-speech
- TTS
capabilities:
default: cpu-piper
metal: metal-piper
uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-piper
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-piper
- name: nvidia-l4t-arm64-llama-cpp
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-llama-cpp
mirrors:
- localai/localai-backends:latest-nvidia-l4t-arm64-llama-cpp
- name: nvidia-l4t-arm64-llama-cpp-development
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-llama-cpp
mirrors:
- localai/localai-backends:master-nvidia-l4t-arm64-llama-cpp
- name: cuda13-nvidia-l4t-arm64-llama-cpp
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-llama-cpp
mirrors:
- localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-llama-cpp
- name: cuda13-nvidia-l4t-arm64-llama-cpp-development
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-llama-cpp
mirrors:
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-llama-cpp
- name: cpu-llama-cpp
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-llama-cpp
mirrors:
- localai/localai-backends:latest-cpu-llama-cpp
- name: cpu-llama-cpp-development
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:master-cpu-llama-cpp
mirrors:
- localai/localai-backends:master-cpu-llama-cpp
- name: cuda12-llama-cpp
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-llama-cpp
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-12-llama-cpp
- name: rocm-llama-cpp
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-llama-cpp
mirrors:
- localai/localai-backends:latest-gpu-rocm-hipblas-llama-cpp
- name: intel-sycl-f32-llama-cpp
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-llama-cpp
mirrors:
- localai/localai-backends:latest-gpu-intel-sycl-f32-llama-cpp
- name: intel-sycl-f16-llama-cpp
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-llama-cpp
mirrors:
- localai/localai-backends:latest-gpu-intel-sycl-f16-llama-cpp
- name: vulkan-llama-cpp
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-llama-cpp
mirrors:
- localai/localai-backends:latest-gpu-vulkan-llama-cpp
- name: vulkan-llama-cpp-development
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-llama-cpp
mirrors:
- localai/localai-backends:master-gpu-vulkan-llama-cpp
- name: metal-llama-cpp
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-llama-cpp
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-llama-cpp
- name: metal-llama-cpp-development
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-llama-cpp
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-llama-cpp
- name: cuda12-llama-cpp-development
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-llama-cpp
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-12-llama-cpp
- name: rocm-llama-cpp-development
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-llama-cpp
mirrors:
- localai/localai-backends:master-gpu-rocm-hipblas-llama-cpp
- name: intel-sycl-f32-llama-cpp-development
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-llama-cpp
mirrors:
- localai/localai-backends:master-gpu-intel-sycl-f32-llama-cpp
- name: intel-sycl-f16-llama-cpp-development
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-llama-cpp
mirrors:
- localai/localai-backends:master-gpu-intel-sycl-f16-llama-cpp
- name: cuda13-llama-cpp
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-llama-cpp
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-13-llama-cpp
- name: cuda13-llama-cpp-development
alias: llama-cpp
license: mit
icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
description: |
LLM inference in C/C++
urls:
- https://github.com/ggerganov/llama.cpp
tags:
- text-to-text
- text-to-speech
- TTS
- LLM
- CPU
- GPU
- Metal
- CUDA
- HIP
capabilities:
amd: rocm-llama-cpp
default: cpu-llama-cpp
intel: intel-sycl-f16-llama-cpp
metal: metal-llama-cpp
nvidia: cuda12-llama-cpp
nvidia-cuda-12: cuda12-llama-cpp
nvidia-cuda-13: cuda13-llama-cpp
nvidia-l4t: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp
vulkan: vulkan-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-llama-cpp
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-13-llama-cpp
- name: cpu-ik-llama-cpp
alias: ik-llama-cpp
license: mit
description: |
Fork of llama.cpp optimized for CPU performance by ikawrakow
urls:
- https://github.com/ikawrakow/ik_llama.cpp
tags:
- text-to-text
- LLM
- CPU
capabilities:
default: cpu-ik-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-ik-llama-cpp
mirrors:
- localai/localai-backends:latest-cpu-ik-llama-cpp
- name: cpu-ik-llama-cpp-development
alias: ik-llama-cpp
license: mit
description: |
Fork of llama.cpp optimized for CPU performance by ikawrakow
urls:
- https://github.com/ikawrakow/ik_llama.cpp
tags:
- text-to-text
- LLM
- CPU
capabilities:
default: cpu-ik-llama-cpp
uri: quay.io/go-skynet/local-ai-backends:master-cpu-ik-llama-cpp
mirrors:
- localai/localai-backends:master-cpu-ik-llama-cpp
- name: cpu-turboquant
alias: turboquant
license: mit
description: |
Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme.
Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama.
urls:
- https://github.com/TheTom/llama-cpp-turboquant
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- turboquant
- kv-cache
capabilities:
amd: rocm-turboquant
default: cpu-turboquant
intel: intel-sycl-f16-turboquant
nvidia: cuda12-turboquant
nvidia-cuda-12: cuda12-turboquant
nvidia-cuda-13: cuda13-turboquant
nvidia-l4t: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant
vulkan: vulkan-turboquant
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-turboquant
mirrors:
- localai/localai-backends:latest-cpu-turboquant
- name: cpu-turboquant-development
alias: turboquant
license: mit
description: |
Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme.
Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama.
urls:
- https://github.com/TheTom/llama-cpp-turboquant
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- turboquant
- kv-cache
capabilities:
amd: rocm-turboquant
default: cpu-turboquant
intel: intel-sycl-f16-turboquant
nvidia: cuda12-turboquant
nvidia-cuda-12: cuda12-turboquant
nvidia-cuda-13: cuda13-turboquant
nvidia-l4t: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant
vulkan: vulkan-turboquant
uri: quay.io/go-skynet/local-ai-backends:master-cpu-turboquant
mirrors:
- localai/localai-backends:master-cpu-turboquant
- name: cuda12-turboquant
alias: turboquant
license: mit
description: |
Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme.
Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama.
urls:
- https://github.com/TheTom/llama-cpp-turboquant
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- turboquant
- kv-cache
capabilities:
amd: rocm-turboquant
default: cpu-turboquant
intel: intel-sycl-f16-turboquant
nvidia: cuda12-turboquant
nvidia-cuda-12: cuda12-turboquant
nvidia-cuda-13: cuda13-turboquant
nvidia-l4t: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant
vulkan: vulkan-turboquant
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-turboquant
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-12-turboquant
- name: cuda12-turboquant-development
alias: turboquant
license: mit
description: |
Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme.
Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama.
urls:
- https://github.com/TheTom/llama-cpp-turboquant
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- turboquant
- kv-cache
capabilities:
amd: rocm-turboquant
default: cpu-turboquant
intel: intel-sycl-f16-turboquant
nvidia: cuda12-turboquant
nvidia-cuda-12: cuda12-turboquant
nvidia-cuda-13: cuda13-turboquant
nvidia-l4t: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant
vulkan: vulkan-turboquant
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-turboquant
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-12-turboquant
- name: cuda13-turboquant
alias: turboquant
license: mit
description: |
Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme.
Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama.
urls:
- https://github.com/TheTom/llama-cpp-turboquant
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- turboquant
- kv-cache
capabilities:
amd: rocm-turboquant
default: cpu-turboquant
intel: intel-sycl-f16-turboquant
nvidia: cuda12-turboquant
nvidia-cuda-12: cuda12-turboquant
nvidia-cuda-13: cuda13-turboquant
nvidia-l4t: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant
vulkan: vulkan-turboquant
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-turboquant
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-13-turboquant
- name: cuda13-turboquant-development
alias: turboquant
license: mit
description: |
Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme.
Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama.
urls:
- https://github.com/TheTom/llama-cpp-turboquant
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- turboquant
- kv-cache
capabilities:
amd: rocm-turboquant
default: cpu-turboquant
intel: intel-sycl-f16-turboquant
nvidia: cuda12-turboquant
nvidia-cuda-12: cuda12-turboquant
nvidia-cuda-13: cuda13-turboquant
nvidia-l4t: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant
vulkan: vulkan-turboquant
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-turboquant
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-13-turboquant
- name: rocm-turboquant
alias: turboquant
license: mit
description: |
Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme.
Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama.
urls:
- https://github.com/TheTom/llama-cpp-turboquant
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- turboquant
- kv-cache
capabilities:
amd: rocm-turboquant
default: cpu-turboquant
intel: intel-sycl-f16-turboquant
nvidia: cuda12-turboquant
nvidia-cuda-12: cuda12-turboquant
nvidia-cuda-13: cuda13-turboquant
nvidia-l4t: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant
vulkan: vulkan-turboquant
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-turboquant
mirrors:
- localai/localai-backends:latest-gpu-rocm-hipblas-turboquant
- name: rocm-turboquant-development
alias: turboquant
license: mit
description: |
Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme.
Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama.
urls:
- https://github.com/TheTom/llama-cpp-turboquant
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- turboquant
- kv-cache
capabilities:
amd: rocm-turboquant
default: cpu-turboquant
intel: intel-sycl-f16-turboquant
nvidia: cuda12-turboquant
nvidia-cuda-12: cuda12-turboquant
nvidia-cuda-13: cuda13-turboquant
nvidia-l4t: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant
vulkan: vulkan-turboquant
uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-turboquant
mirrors:
- localai/localai-backends:master-gpu-rocm-hipblas-turboquant
- name: intel-sycl-f32-turboquant
alias: turboquant
license: mit
description: |
Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme.
Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama.
urls:
- https://github.com/TheTom/llama-cpp-turboquant
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- turboquant
- kv-cache
capabilities:
amd: rocm-turboquant
default: cpu-turboquant
intel: intel-sycl-f16-turboquant
nvidia: cuda12-turboquant
nvidia-cuda-12: cuda12-turboquant
nvidia-cuda-13: cuda13-turboquant
nvidia-l4t: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant
vulkan: vulkan-turboquant
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-turboquant
mirrors:
- localai/localai-backends:latest-gpu-intel-sycl-f32-turboquant
- name: intel-sycl-f32-turboquant-development
alias: turboquant
license: mit
description: |
Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme.
Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama.
urls:
- https://github.com/TheTom/llama-cpp-turboquant
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- turboquant
- kv-cache
capabilities:
amd: rocm-turboquant
default: cpu-turboquant
intel: intel-sycl-f16-turboquant
nvidia: cuda12-turboquant
nvidia-cuda-12: cuda12-turboquant
nvidia-cuda-13: cuda13-turboquant
nvidia-l4t: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant
vulkan: vulkan-turboquant
uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-turboquant
mirrors:
- localai/localai-backends:master-gpu-intel-sycl-f32-turboquant
- name: intel-sycl-f16-turboquant
alias: turboquant
license: mit
description: |
Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme.
Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama.
urls:
- https://github.com/TheTom/llama-cpp-turboquant
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- turboquant
- kv-cache
capabilities:
amd: rocm-turboquant
default: cpu-turboquant
intel: intel-sycl-f16-turboquant
nvidia: cuda12-turboquant
nvidia-cuda-12: cuda12-turboquant
nvidia-cuda-13: cuda13-turboquant
nvidia-l4t: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant
vulkan: vulkan-turboquant
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-turboquant
mirrors:
- localai/localai-backends:latest-gpu-intel-sycl-f16-turboquant
- name: intel-sycl-f16-turboquant-development
alias: turboquant
license: mit
description: |
Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme.
Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama.
urls:
- https://github.com/TheTom/llama-cpp-turboquant
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- turboquant
- kv-cache
capabilities:
amd: rocm-turboquant
default: cpu-turboquant
intel: intel-sycl-f16-turboquant
nvidia: cuda12-turboquant
nvidia-cuda-12: cuda12-turboquant
nvidia-cuda-13: cuda13-turboquant
nvidia-l4t: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant
vulkan: vulkan-turboquant
uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-turboquant
mirrors:
- localai/localai-backends:master-gpu-intel-sycl-f16-turboquant
- name: vulkan-turboquant
alias: turboquant
license: mit
description: |
Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme.
Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama.
urls:
- https://github.com/TheTom/llama-cpp-turboquant
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- turboquant
- kv-cache
capabilities:
amd: rocm-turboquant
default: cpu-turboquant
intel: intel-sycl-f16-turboquant
nvidia: cuda12-turboquant
nvidia-cuda-12: cuda12-turboquant
nvidia-cuda-13: cuda13-turboquant
nvidia-l4t: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant
vulkan: vulkan-turboquant
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-turboquant
mirrors:
- localai/localai-backends:latest-gpu-vulkan-turboquant
- name: vulkan-turboquant-development
alias: turboquant
license: mit
description: |
Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme.
Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama.
urls:
- https://github.com/TheTom/llama-cpp-turboquant
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- turboquant
- kv-cache
capabilities:
amd: rocm-turboquant
default: cpu-turboquant
intel: intel-sycl-f16-turboquant
nvidia: cuda12-turboquant
nvidia-cuda-12: cuda12-turboquant
nvidia-cuda-13: cuda13-turboquant
nvidia-l4t: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant
vulkan: vulkan-turboquant
uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-turboquant
mirrors:
- localai/localai-backends:master-gpu-vulkan-turboquant
- name: nvidia-l4t-arm64-turboquant
alias: turboquant
license: mit
description: |
Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme.
Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama.
urls:
- https://github.com/TheTom/llama-cpp-turboquant
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- turboquant
- kv-cache
capabilities:
amd: rocm-turboquant
default: cpu-turboquant
intel: intel-sycl-f16-turboquant
nvidia: cuda12-turboquant
nvidia-cuda-12: cuda12-turboquant
nvidia-cuda-13: cuda13-turboquant
nvidia-l4t: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant
vulkan: vulkan-turboquant
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-turboquant
mirrors:
- localai/localai-backends:latest-nvidia-l4t-arm64-turboquant
- name: nvidia-l4t-arm64-turboquant-development
alias: turboquant
license: mit
description: |
Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme.
Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama.
urls:
- https://github.com/TheTom/llama-cpp-turboquant
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- turboquant
- kv-cache
capabilities:
amd: rocm-turboquant
default: cpu-turboquant
intel: intel-sycl-f16-turboquant
nvidia: cuda12-turboquant
nvidia-cuda-12: cuda12-turboquant
nvidia-cuda-13: cuda13-turboquant
nvidia-l4t: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant
vulkan: vulkan-turboquant
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-turboquant
mirrors:
- localai/localai-backends:master-nvidia-l4t-arm64-turboquant
- name: cuda13-nvidia-l4t-arm64-turboquant
alias: turboquant
license: mit
description: |
Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme.
Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama.
urls:
- https://github.com/TheTom/llama-cpp-turboquant
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- turboquant
- kv-cache
capabilities:
amd: rocm-turboquant
default: cpu-turboquant
intel: intel-sycl-f16-turboquant
nvidia: cuda12-turboquant
nvidia-cuda-12: cuda12-turboquant
nvidia-cuda-13: cuda13-turboquant
nvidia-l4t: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant
vulkan: vulkan-turboquant
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-turboquant
mirrors:
- localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-turboquant
- name: cuda13-nvidia-l4t-arm64-turboquant-development
alias: turboquant
license: mit
description: |
Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme.
Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama.
urls:
- https://github.com/TheTom/llama-cpp-turboquant
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- turboquant
- kv-cache
capabilities:
amd: rocm-turboquant
default: cpu-turboquant
intel: intel-sycl-f16-turboquant
nvidia: cuda12-turboquant
nvidia-cuda-12: cuda12-turboquant
nvidia-cuda-13: cuda13-turboquant
nvidia-l4t: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant
vulkan: vulkan-turboquant
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-turboquant
mirrors:
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-turboquant
- name: cpu-bonsai
alias: bonsai
license: apache-2.0
description: |
Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit)
weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses
the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives
these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp
backend.
urls:
- https://github.com/PrismML-Eng/llama.cpp
- https://huggingface.co/prism-ml
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- bonsai
- 1-bit
- ternary
capabilities:
amd: rocm-bonsai
default: cpu-bonsai
intel: intel-sycl-f16-bonsai
nvidia: cuda12-bonsai
nvidia-cuda-12: cuda12-bonsai
nvidia-cuda-13: cuda13-bonsai
nvidia-l4t: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai
vulkan: vulkan-bonsai
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-bonsai
mirrors:
- localai/localai-backends:latest-cpu-bonsai
- name: cpu-bonsai-development
alias: bonsai
license: apache-2.0
description: |
Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit)
weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses
the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives
these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp
backend.
urls:
- https://github.com/PrismML-Eng/llama.cpp
- https://huggingface.co/prism-ml
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- bonsai
- 1-bit
- ternary
capabilities:
amd: rocm-bonsai
default: cpu-bonsai
intel: intel-sycl-f16-bonsai
nvidia: cuda12-bonsai
nvidia-cuda-12: cuda12-bonsai
nvidia-cuda-13: cuda13-bonsai
nvidia-l4t: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai
vulkan: vulkan-bonsai
uri: quay.io/go-skynet/local-ai-backends:master-cpu-bonsai
mirrors:
- localai/localai-backends:master-cpu-bonsai
- name: cuda12-bonsai
alias: bonsai
license: apache-2.0
description: |
Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit)
weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses
the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives
these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp
backend.
urls:
- https://github.com/PrismML-Eng/llama.cpp
- https://huggingface.co/prism-ml
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- bonsai
- 1-bit
- ternary
capabilities:
amd: rocm-bonsai
default: cpu-bonsai
intel: intel-sycl-f16-bonsai
nvidia: cuda12-bonsai
nvidia-cuda-12: cuda12-bonsai
nvidia-cuda-13: cuda13-bonsai
nvidia-l4t: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai
vulkan: vulkan-bonsai
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-bonsai
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-12-bonsai
- name: cuda12-bonsai-development
alias: bonsai
license: apache-2.0
description: |
Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit)
weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses
the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives
these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp
backend.
urls:
- https://github.com/PrismML-Eng/llama.cpp
- https://huggingface.co/prism-ml
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- bonsai
- 1-bit
- ternary
capabilities:
amd: rocm-bonsai
default: cpu-bonsai
intel: intel-sycl-f16-bonsai
nvidia: cuda12-bonsai
nvidia-cuda-12: cuda12-bonsai
nvidia-cuda-13: cuda13-bonsai
nvidia-l4t: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai
vulkan: vulkan-bonsai
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-bonsai
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-12-bonsai
- name: cuda13-bonsai
alias: bonsai
license: apache-2.0
description: |
Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit)
weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses
the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives
these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp
backend.
urls:
- https://github.com/PrismML-Eng/llama.cpp
- https://huggingface.co/prism-ml
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- bonsai
- 1-bit
- ternary
capabilities:
amd: rocm-bonsai
default: cpu-bonsai
intel: intel-sycl-f16-bonsai
nvidia: cuda12-bonsai
nvidia-cuda-12: cuda12-bonsai
nvidia-cuda-13: cuda13-bonsai
nvidia-l4t: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai
vulkan: vulkan-bonsai
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-bonsai
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-13-bonsai
- name: cuda13-bonsai-development
alias: bonsai
license: apache-2.0
description: |
Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit)
weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses
the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives
these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp
backend.
urls:
- https://github.com/PrismML-Eng/llama.cpp
- https://huggingface.co/prism-ml
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- bonsai
- 1-bit
- ternary
capabilities:
amd: rocm-bonsai
default: cpu-bonsai
intel: intel-sycl-f16-bonsai
nvidia: cuda12-bonsai
nvidia-cuda-12: cuda12-bonsai
nvidia-cuda-13: cuda13-bonsai
nvidia-l4t: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai
vulkan: vulkan-bonsai
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-bonsai
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-13-bonsai
- name: rocm-bonsai
alias: bonsai
license: apache-2.0
description: |
Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit)
weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses
the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives
these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp
backend.
urls:
- https://github.com/PrismML-Eng/llama.cpp
- https://huggingface.co/prism-ml
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- bonsai
- 1-bit
- ternary
capabilities:
amd: rocm-bonsai
default: cpu-bonsai
intel: intel-sycl-f16-bonsai
nvidia: cuda12-bonsai
nvidia-cuda-12: cuda12-bonsai
nvidia-cuda-13: cuda13-bonsai
nvidia-l4t: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai
vulkan: vulkan-bonsai
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-bonsai
mirrors:
- localai/localai-backends:latest-gpu-rocm-hipblas-bonsai
- name: rocm-bonsai-development
alias: bonsai
license: apache-2.0
description: |
Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit)
weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses
the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives
these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp
backend.
urls:
- https://github.com/PrismML-Eng/llama.cpp
- https://huggingface.co/prism-ml
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- bonsai
- 1-bit
- ternary
capabilities:
amd: rocm-bonsai
default: cpu-bonsai
intel: intel-sycl-f16-bonsai
nvidia: cuda12-bonsai
nvidia-cuda-12: cuda12-bonsai
nvidia-cuda-13: cuda13-bonsai
nvidia-l4t: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai
vulkan: vulkan-bonsai
uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-bonsai
mirrors:
- localai/localai-backends:master-gpu-rocm-hipblas-bonsai
- name: intel-sycl-f32-bonsai
alias: bonsai
license: apache-2.0
description: |
Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit)
weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses
the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives
these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp
backend.
urls:
- https://github.com/PrismML-Eng/llama.cpp
- https://huggingface.co/prism-ml
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- bonsai
- 1-bit
- ternary
capabilities:
amd: rocm-bonsai
default: cpu-bonsai
intel: intel-sycl-f16-bonsai
nvidia: cuda12-bonsai
nvidia-cuda-12: cuda12-bonsai
nvidia-cuda-13: cuda13-bonsai
nvidia-l4t: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai
vulkan: vulkan-bonsai
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-bonsai
mirrors:
- localai/localai-backends:latest-gpu-intel-sycl-f32-bonsai
- name: intel-sycl-f32-bonsai-development
alias: bonsai
license: apache-2.0
description: |
Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit)
weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses
the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives
these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp
backend.
urls:
- https://github.com/PrismML-Eng/llama.cpp
- https://huggingface.co/prism-ml
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- bonsai
- 1-bit
- ternary
capabilities:
amd: rocm-bonsai
default: cpu-bonsai
intel: intel-sycl-f16-bonsai
nvidia: cuda12-bonsai
nvidia-cuda-12: cuda12-bonsai
nvidia-cuda-13: cuda13-bonsai
nvidia-l4t: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai
vulkan: vulkan-bonsai
uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-bonsai
mirrors:
- localai/localai-backends:master-gpu-intel-sycl-f32-bonsai
- name: intel-sycl-f16-bonsai
alias: bonsai
license: apache-2.0
description: |
Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit)
weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses
the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives
these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp
backend.
urls:
- https://github.com/PrismML-Eng/llama.cpp
- https://huggingface.co/prism-ml
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- bonsai
- 1-bit
- ternary
capabilities:
amd: rocm-bonsai
default: cpu-bonsai
intel: intel-sycl-f16-bonsai
nvidia: cuda12-bonsai
nvidia-cuda-12: cuda12-bonsai
nvidia-cuda-13: cuda13-bonsai
nvidia-l4t: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai
vulkan: vulkan-bonsai
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-bonsai
mirrors:
- localai/localai-backends:latest-gpu-intel-sycl-f16-bonsai
- name: intel-sycl-f16-bonsai-development
alias: bonsai
license: apache-2.0
description: |
Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit)
weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses
the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives
these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp
backend.
urls:
- https://github.com/PrismML-Eng/llama.cpp
- https://huggingface.co/prism-ml
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- bonsai
- 1-bit
- ternary
capabilities:
amd: rocm-bonsai
default: cpu-bonsai
intel: intel-sycl-f16-bonsai
nvidia: cuda12-bonsai
nvidia-cuda-12: cuda12-bonsai
nvidia-cuda-13: cuda13-bonsai
nvidia-l4t: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai
vulkan: vulkan-bonsai
uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-bonsai
mirrors:
- localai/localai-backends:master-gpu-intel-sycl-f16-bonsai
- name: vulkan-bonsai
alias: bonsai
license: apache-2.0
description: |
Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit)
weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses
the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives
these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp
backend.
urls:
- https://github.com/PrismML-Eng/llama.cpp
- https://huggingface.co/prism-ml
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- bonsai
- 1-bit
- ternary
capabilities:
amd: rocm-bonsai
default: cpu-bonsai
intel: intel-sycl-f16-bonsai
nvidia: cuda12-bonsai
nvidia-cuda-12: cuda12-bonsai
nvidia-cuda-13: cuda13-bonsai
nvidia-l4t: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai
vulkan: vulkan-bonsai
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-bonsai
mirrors:
- localai/localai-backends:latest-gpu-vulkan-bonsai
- name: vulkan-bonsai-development
alias: bonsai
license: apache-2.0
description: |
Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit)
weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses
the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives
these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp
backend.
urls:
- https://github.com/PrismML-Eng/llama.cpp
- https://huggingface.co/prism-ml
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- bonsai
- 1-bit
- ternary
capabilities:
amd: rocm-bonsai
default: cpu-bonsai
intel: intel-sycl-f16-bonsai
nvidia: cuda12-bonsai
nvidia-cuda-12: cuda12-bonsai
nvidia-cuda-13: cuda13-bonsai
nvidia-l4t: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai
vulkan: vulkan-bonsai
uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-bonsai
mirrors:
- localai/localai-backends:master-gpu-vulkan-bonsai
- name: nvidia-l4t-arm64-bonsai
alias: bonsai
license: apache-2.0
description: |
Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit)
weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses
the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives
these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp
backend.
urls:
- https://github.com/PrismML-Eng/llama.cpp
- https://huggingface.co/prism-ml
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- bonsai
- 1-bit
- ternary
capabilities:
amd: rocm-bonsai
default: cpu-bonsai
intel: intel-sycl-f16-bonsai
nvidia: cuda12-bonsai
nvidia-cuda-12: cuda12-bonsai
nvidia-cuda-13: cuda13-bonsai
nvidia-l4t: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai
vulkan: vulkan-bonsai
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-bonsai
mirrors:
- localai/localai-backends:latest-nvidia-l4t-arm64-bonsai
- name: nvidia-l4t-arm64-bonsai-development
alias: bonsai
license: apache-2.0
description: |
Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit)
weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses
the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives
these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp
backend.
urls:
- https://github.com/PrismML-Eng/llama.cpp
- https://huggingface.co/prism-ml
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- bonsai
- 1-bit
- ternary
capabilities:
amd: rocm-bonsai
default: cpu-bonsai
intel: intel-sycl-f16-bonsai
nvidia: cuda12-bonsai
nvidia-cuda-12: cuda12-bonsai
nvidia-cuda-13: cuda13-bonsai
nvidia-l4t: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai
vulkan: vulkan-bonsai
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-bonsai
mirrors:
- localai/localai-backends:master-nvidia-l4t-arm64-bonsai
- name: cuda13-nvidia-l4t-arm64-bonsai
alias: bonsai
license: apache-2.0
description: |
Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit)
weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses
the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives
these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp
backend.
urls:
- https://github.com/PrismML-Eng/llama.cpp
- https://huggingface.co/prism-ml
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- bonsai
- 1-bit
- ternary
capabilities:
amd: rocm-bonsai
default: cpu-bonsai
intel: intel-sycl-f16-bonsai
nvidia: cuda12-bonsai
nvidia-cuda-12: cuda12-bonsai
nvidia-cuda-13: cuda13-bonsai
nvidia-l4t: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai
vulkan: vulkan-bonsai
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-bonsai
mirrors:
- localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-bonsai
- name: cuda13-nvidia-l4t-arm64-bonsai-development
alias: bonsai
license: apache-2.0
description: |
Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit)
weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses
the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives
these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp
backend.
urls:
- https://github.com/PrismML-Eng/llama.cpp
- https://huggingface.co/prism-ml
tags:
- text-to-text
- LLM
- CPU
- GPU
- CUDA
- HIP
- bonsai
- 1-bit
- ternary
capabilities:
amd: rocm-bonsai
default: cpu-bonsai
intel: intel-sycl-f16-bonsai
nvidia: cuda12-bonsai
nvidia-cuda-12: cuda12-bonsai
nvidia-cuda-13: cuda13-bonsai
nvidia-l4t: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai
vulkan: vulkan-bonsai
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-bonsai
mirrors:
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-bonsai
- name: cpu-ds4
alias: ds4
license: mit
description: |
antirez/ds4 - DeepSeek V4 Flash inference engine. Single-model,
optimized for Metal (Darwin) and CUDA (Linux). Requires the GGUFs
published at huggingface.co/antirez/deepseek-v4-gguf.
urls:
- https://github.com/antirez/ds4
tags:
- text-to-text
- LLM
- CPU
- CUDA
- Metal
capabilities:
default: cpu-ds4
metal: metal-ds4
metal-darwin-arm64: metal-ds4
nvidia: cuda13-ds4
nvidia-cuda-13: cuda13-ds4
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ds4
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-ds4
mirrors:
- localai/localai-backends:latest-cpu-ds4
- name: cpu-ds4-development
alias: ds4
license: mit
description: |
antirez/ds4 - DeepSeek V4 Flash inference engine. Single-model,
optimized for Metal (Darwin) and CUDA (Linux). Requires the GGUFs
published at huggingface.co/antirez/deepseek-v4-gguf.
urls:
- https://github.com/antirez/ds4
tags:
- text-to-text
- LLM
- CPU
- CUDA
- Metal
capabilities:
default: cpu-ds4
metal: metal-ds4
metal-darwin-arm64: metal-ds4
nvidia: cuda13-ds4
nvidia-cuda-13: cuda13-ds4
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ds4
uri: quay.io/go-skynet/local-ai-backends:master-cpu-ds4
mirrors:
- localai/localai-backends:master-cpu-ds4
- name: cuda13-ds4
alias: ds4
license: mit
description: |
antirez/ds4 - DeepSeek V4 Flash inference engine. Single-model,
optimized for Metal (Darwin) and CUDA (Linux). Requires the GGUFs
published at huggingface.co/antirez/deepseek-v4-gguf.
urls:
- https://github.com/antirez/ds4
tags:
- text-to-text
- LLM
- CPU
- CUDA
- Metal
capabilities:
default: cpu-ds4
metal: metal-ds4
metal-darwin-arm64: metal-ds4
nvidia: cuda13-ds4
nvidia-cuda-13: cuda13-ds4
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ds4
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-ds4
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-13-ds4
- name: cuda13-ds4-development
alias: ds4
license: mit
description: |
antirez/ds4 - DeepSeek V4 Flash inference engine. Single-model,
optimized for Metal (Darwin) and CUDA (Linux). Requires the GGUFs
published at huggingface.co/antirez/deepseek-v4-gguf.
urls:
- https://github.com/antirez/ds4
tags:
- text-to-text
- LLM
- CPU
- CUDA
- Metal
capabilities:
default: cpu-ds4
metal: metal-ds4
metal-darwin-arm64: metal-ds4
nvidia: cuda13-ds4
nvidia-cuda-13: cuda13-ds4
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ds4
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-ds4
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-13-ds4
- name: cuda13-nvidia-l4t-arm64-ds4
alias: ds4
license: mit
description: |
antirez/ds4 - DeepSeek V4 Flash inference engine. Single-model,
optimized for Metal (Darwin) and CUDA (Linux). Requires the GGUFs
published at huggingface.co/antirez/deepseek-v4-gguf.
urls:
- https://github.com/antirez/ds4
tags:
- text-to-text
- LLM
- CPU
- CUDA
- Metal
capabilities:
default: cpu-ds4
metal: metal-ds4
metal-darwin-arm64: metal-ds4
nvidia: cuda13-ds4
nvidia-cuda-13: cuda13-ds4
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ds4
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-ds4
mirrors:
- localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-ds4
- name: cuda13-nvidia-l4t-arm64-ds4-development
alias: ds4
license: mit
description: |
antirez/ds4 - DeepSeek V4 Flash inference engine. Single-model,
optimized for Metal (Darwin) and CUDA (Linux). Requires the GGUFs
published at huggingface.co/antirez/deepseek-v4-gguf.
urls:
- https://github.com/antirez/ds4
tags:
- text-to-text
- LLM
- CPU
- CUDA
- Metal
capabilities:
default: cpu-ds4
metal: metal-ds4
metal-darwin-arm64: metal-ds4
nvidia: cuda13-ds4
nvidia-cuda-13: cuda13-ds4
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ds4
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-ds4
mirrors:
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-ds4
- name: metal-ds4
alias: ds4
license: mit
description: |
antirez/ds4 - DeepSeek V4 Flash inference engine. Single-model,
optimized for Metal (Darwin) and CUDA (Linux). Requires the GGUFs
published at huggingface.co/antirez/deepseek-v4-gguf.
urls:
- https://github.com/antirez/ds4
tags:
- text-to-text
- LLM
- CPU
- CUDA
- Metal
capabilities:
default: cpu-ds4
metal: metal-ds4
metal-darwin-arm64: metal-ds4
nvidia: cuda13-ds4
nvidia-cuda-13: cuda13-ds4
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ds4
uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-ds4
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-ds4
- name: metal-ds4-development
alias: ds4
license: mit
description: |
antirez/ds4 - DeepSeek V4 Flash inference engine. Single-model,
optimized for Metal (Darwin) and CUDA (Linux). Requires the GGUFs
published at huggingface.co/antirez/deepseek-v4-gguf.
urls:
- https://github.com/antirez/ds4
tags:
- text-to-text
- LLM
- CPU
- CUDA
- Metal
capabilities:
default: cpu-ds4
metal: metal-ds4
metal-darwin-arm64: metal-ds4
nvidia: cuda13-ds4
nvidia-cuda-13: cuda13-ds4
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ds4
uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-ds4
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-ds4
- name: whisper-development
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper-development
default: cpu-whisper-development
intel: intel-sycl-f16-whisper-development
metal: metal-whisper-development
nvidia: cuda12-whisper-development
nvidia-cuda-12: cuda12-whisper-development
nvidia-cuda-13: cuda13-whisper-development
nvidia-l4t: nvidia-l4t-arm64-whisper-development
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper-development
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper-development
vulkan: vulkan-whisper-development
- name: nvidia-l4t-arm64-whisper
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-whisper
mirrors:
- localai/localai-backends:latest-nvidia-l4t-arm64-whisper
- name: nvidia-l4t-arm64-whisper-development
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-whisper
mirrors:
- localai/localai-backends:master-nvidia-l4t-arm64-whisper
- name: cuda13-nvidia-l4t-arm64-whisper
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-whisper
mirrors:
- localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-whisper
- name: cuda13-nvidia-l4t-arm64-whisper-development
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-whisper
mirrors:
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-whisper
- name: cpu-whisper
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-whisper
mirrors:
- localai/localai-backends:latest-cpu-whisper
- name: metal-whisper
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-whisper
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-whisper
- name: metal-whisper-development
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-whisper
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-whisper
- name: cpu-whisper-development
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
uri: quay.io/go-skynet/local-ai-backends:master-cpu-whisper
mirrors:
- localai/localai-backends:master-cpu-whisper
- name: cuda12-whisper
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-whisper
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-12-whisper
- name: rocm-whisper
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-whisper
mirrors:
- localai/localai-backends:latest-gpu-rocm-hipblas-whisper
- name: intel-sycl-f32-whisper
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-whisper
mirrors:
- localai/localai-backends:latest-gpu-intel-sycl-f32-whisper
- name: intel-sycl-f16-whisper
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-whisper
mirrors:
- localai/localai-backends:latest-gpu-intel-sycl-f16-whisper
- name: vulkan-whisper
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-whisper
mirrors:
- localai/localai-backends:latest-gpu-vulkan-whisper
- name: vulkan-whisper-development
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-whisper
mirrors:
- localai/localai-backends:master-gpu-vulkan-whisper
- name: cuda12-whisper-development
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-whisper
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-12-whisper
- name: rocm-whisper-development
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-whisper
mirrors:
- localai/localai-backends:master-gpu-rocm-hipblas-whisper
- name: intel-sycl-f32-whisper-development
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-whisper
mirrors:
- localai/localai-backends:master-gpu-intel-sycl-f32-whisper
- name: intel-sycl-f16-whisper-development
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-whisper
mirrors:
- localai/localai-backends:master-gpu-intel-sycl-f16-whisper
- name: cuda13-whisper
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-whisper
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-13-whisper
- name: cuda13-whisper-development
alias: whisper
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
Port of OpenAI's Whisper model in C/C++
urls:
- https://github.com/ggml-org/whisper.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-whisper
default: cpu-whisper
intel: intel-sycl-f16-whisper
metal: metal-whisper
nvidia: cuda12-whisper
nvidia-cuda-12: cuda12-whisper
nvidia-cuda-13: cuda13-whisper
nvidia-l4t: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper
vulkan: vulkan-whisper
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-whisper
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-13-whisper
- name: crispasr-development
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr-development
default: cpu-crispasr-development
intel: intel-sycl-f16-crispasr-development
metal: metal-crispasr-development
nvidia: cuda12-crispasr-development
nvidia-cuda-12: cuda12-crispasr-development
nvidia-cuda-13: cuda13-crispasr-development
nvidia-l4t: nvidia-l4t-arm64-crispasr-development
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr-development
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr-development
vulkan: vulkan-crispasr-development
- name: nvidia-l4t-arm64-crispasr
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-crispasr
mirrors:
- localai/localai-backends:latest-nvidia-l4t-arm64-crispasr
- name: nvidia-l4t-arm64-crispasr-development
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-crispasr
mirrors:
- localai/localai-backends:master-nvidia-l4t-arm64-crispasr
- name: cuda13-nvidia-l4t-arm64-crispasr
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-crispasr
mirrors:
- localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-crispasr
- name: cuda13-nvidia-l4t-arm64-crispasr-development
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-crispasr
mirrors:
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-crispasr
- name: cpu-crispasr
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
uri: quay.io/go-skynet/local-ai-backends:latest-cpu-crispasr
mirrors:
- localai/localai-backends:latest-cpu-crispasr
- name: metal-crispasr
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-crispasr
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-crispasr
- name: metal-crispasr-development
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-crispasr
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-crispasr
- name: cpu-crispasr-development
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
uri: quay.io/go-skynet/local-ai-backends:master-cpu-crispasr
mirrors:
- localai/localai-backends:master-cpu-crispasr
- name: cuda12-crispasr
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-crispasr
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-12-crispasr
- name: rocm-crispasr
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-crispasr
mirrors:
- localai/localai-backends:latest-gpu-rocm-hipblas-crispasr
- name: intel-sycl-f32-crispasr
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-crispasr
mirrors:
- localai/localai-backends:latest-gpu-intel-sycl-f32-crispasr
- name: intel-sycl-f16-crispasr
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-crispasr
mirrors:
- localai/localai-backends:latest-gpu-intel-sycl-f16-crispasr
- name: vulkan-crispasr
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-crispasr
mirrors:
- localai/localai-backends:latest-gpu-vulkan-crispasr
- name: vulkan-crispasr-development
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-crispasr
mirrors:
- localai/localai-backends:master-gpu-vulkan-crispasr
- name: cuda12-crispasr-development
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-crispasr
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-12-crispasr
- name: rocm-crispasr-development
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-crispasr
mirrors:
- localai/localai-backends:master-gpu-rocm-hipblas-crispasr
- name: intel-sycl-f32-crispasr-development
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-crispasr
mirrors:
- localai/localai-backends:master-gpu-intel-sycl-f32-crispasr
- name: intel-sycl-f16-crispasr-development
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-crispasr
mirrors:
- localai/localai-backends:master-gpu-intel-sycl-f16-crispasr
- name: cuda13-crispasr
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-crispasr
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-13-crispasr
- name: cuda13-crispasr-development
alias: crispasr
license: mit
icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg
description: |
CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more).
urls:
- https://github.com/CrispStrobe/CrispASR
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-crispasr
default: cpu-crispasr
intel: intel-sycl-f16-crispasr
metal: metal-crispasr
nvidia: cuda12-crispasr
nvidia-cuda-12: cuda12-crispasr
nvidia-cuda-13: cuda13-crispasr
nvidia-l4t: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr
vulkan: vulkan-crispasr
uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-crispasr
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-13-crispasr
- name: parakeet-cpp-development
alias: parakeet-cpp
license: mit
icon: https://avatars.githubusercontent.com/u/95302084
description: |
parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models.
It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription,
and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets.
urls:
- https://github.com/mudler/parakeet.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-parakeet-cpp-development
default: cpu-parakeet-cpp-development
intel: intel-sycl-f16-parakeet-cpp-development
metal: metal-parakeet-cpp-development
nvidia: cuda12-parakeet-cpp-development
nvidia-cuda-12: cuda12-parakeet-cpp-development
nvidia-cuda-13: cuda13-parakeet-cpp-development
nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp-development
nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp-development
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp-development
vulkan: vulkan-parakeet-cpp-development
- name: nvidia-l4t-arm64-parakeet-cpp
alias: parakeet-cpp
license: mit
icon: https://avatars.githubusercontent.com/u/95302084
description: |
parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models.
It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription,
and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets.
urls:
- https://github.com/mudler/parakeet.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilities:
amd: rocm-parakeet-cpp
default: cpu-parakeet-cpp
intel: intel-sycl-f16-parakeet-cpp
metal: metal-parakeet-cpp
nvidia: cuda12-parakeet-cpp
nvidia-cuda-12: cuda12-parakeet-cpp
nvidia-cuda-13: cuda13-parakeet-cpp
nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp
nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp
nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp
vulkan: vulkan-parakeet-cpp
uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-parakeet-cpp
mirrors:
- localai/localai-backends:latest-nvidia-l4t-arm64-parakeet-cpp
- name: nvidia-l4t-arm64-parakeet-cpp-development
alias: parakeet-cpp
license: mit
icon: https://avatars.githubusercontent.com/u/95302084
description: |
parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models.
It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription,
and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets.
urls:
- https://github.com/mudler/parakeet.cpp
tags:
- audio-transcription
- CPU
- GPU
- CUDA
- HIP
capabilit