Edit Models filters

Model Tree

Apps

Docker Model Runner

Inference Providers

OVHcloud AI Endpoints

HF Inference API

One-click Deployment

Inference Endpoints

Microsoft Foundry

Amazon SageMaker AI

Misc

text-generation-inference

Eval Results (legacy)

text-embeddings-inference

4-bit precision

8-bit precision

Mixture of Experts

Carbon Emissions

Models

373

Base only

Active filters: mlx-audio

mlx-community/VibeVoice-ASR-8bit

Automatic Speech Recognition • 8B • Updated Jan 23 • 138 • 4

mlx-community/VibeVoice-ASR-6bit

Automatic Speech Recognition • 8B • Updated Jan 23 • 28 • 1

mlx-community/VibeVoice-ASR-5bit

Automatic Speech Recognition • 8B • Updated Jan 23 • 28

mlx-community/VibeVoice-ASR-4bit

Automatic Speech Recognition • 8B • Updated Jan 23 • 616 • 26

mlx-community/VibeVoice-ASR-bf16

Automatic Speech Recognition • 8B • Updated Jan 23 • 119 • 5

kyr0/qwen3-TTS-12Hz-0.6B-Base-4bit-partial-quantization

Text-to-Speech • 0.4B • Updated Jan 23 • 34 • 1

kyr0/qwen3-TTS-12Hz-0.6B-CustomVoice-4bit-partial-quantization

Text-to-Speech • 0.4B • Updated Jan 23 • 29 • 1

smdesai/Qwen3-TTS-12Hz-1.7B-VoiceDesign-4bit

Text-to-Speech • 0.3B • Updated Jan 25 • 15 • 1

mlx-community/Qwen3-ASR-1.7B-4bit

0.6B • Updated Jan 29 • 1.11k • 1

mlx-community/Qwen3-ASR-1.7B-5bit

0.6B • Updated Jan 29 • 110 • 1

mlx-community/Qwen3-ASR-1.7B-6bit

0.7B • Updated Jan 29 • 433

mlx-community/Qwen3-ASR-1.7B-8bit

0.8B • Updated Jan 29 • 3.52k • 17

mlx-community/Qwen3-ASR-1.7B-bf16

2B • Updated Jan 29 • 1.67k • 9

mlx-community/Qwen3-ASR-0.6B-bf16

0.8B • Updated Jan 29 • 301 • 3

mlx-community/Qwen3-ASR-0.6B-5bit

0.3B • Updated Jan 29 • 57

mlx-community/Qwen3-ASR-0.6B-6bit

0.3B • Updated Jan 29 • 194

mlx-community/Qwen3-ASR-0.6B-8bit

0.4B • Updated Jan 29 • 205k • 4

mlx-community/Qwen3-ForcedAligner-0.6B-bf16

0.9B • Updated Jan 29 • 149 • 2

mlx-community/Qwen3-ForcedAligner-0.6B-8bit

0.5B • Updated Jan 29 • 875 • 3

mlx-community/Qwen3-ForcedAligner-0.6B-6bit

0.4B • Updated Jan 29 • 9

mlx-community/Qwen3-ForcedAligner-0.6B-5bit

0.4B • Updated Jan 29 • 10

mlx-community/Qwen3-ForcedAligner-0.6B-4bit

0.4B • Updated Jan 29 • 327

smdesai/Qwen3-TTS-12Hz-0.6B-CustomVoice-8bit

Text-to-Speech • 0.5B • Updated Jan 30 • 10

mlx-community/Soprano-1.1-80M-bf16

Text-to-Speech • 0.1B • Updated Feb 4 • 162 • 2

mlx-community/Soprano-1.1-80M-5bit

Text-to-Speech • 21M • Updated Feb 4 • 170

mlx-community/Soprano-1.1-80M-6bit

Text-to-Speech • 24.5M • Updated Feb 4 • 11

mlx-community/Soprano-1.1-80M-8bit

Text-to-Speech • 31.3M • Updated Feb 4 • 16

mlx-community/Voxtral-Mini-4B-Realtime-2602-fp16

Automatic Speech Recognition • 4B • Updated Feb 9 • 316 • 3

SiddharthaGolu/Qwen3-TTS-12Hz-1.7B-Base-bf16

Text-to-Speech • 2B • Updated Feb 6 • 9

shreyask/voxtral-mini-4b-realtime-mlx-mixed-4-6

1B • Updated Feb 7 • 13