OpenModelStats

mlx-community AI Models

Tracked by OpenModelStats since Aug 23, 2026 · View on Hugging Face ↗

Tracked models
570
Downloads 30D
7.9M
Total downloads
97.3M
Total likes
6,207
Gained 7D
—

Most downloaded

  1. 1parakeet-tdt-0.6b-v2May 10, 20252.2M
  2. 2parakeet-tdt-0.6b-v3Aug 16, 20251.6M
  3. 3gpt-oss-20b-MXFP4-Q8Mar 19, 2026350.7K
  4. 4Qwen3-ASR-0.6B-8bitJan 29, 2026186.7K
  5. 5Kimi-K2.5Jan 27, 2026161.8K
  6. 6Qwen2.5-Coder-7B-Instruct-4bitSep 18, 2024161.1K
  7. 7Qwen3-14B-4bitApr 29, 2025137.2K
  8. 8Devstral-Small-2-24B-Instruct-2512-4bitJul 4, 2026102.8K
  9. 9Qwen3-30B-A3B-Instruct-2507-4bitAug 6, 202599.3K
  10. 10whisper-large-v3-turboApr 12, 202695.5K

Recently updated

  1. 1Octen-Embedding-4B-MLX-4bitAug 24, 20260
  2. 2SenseNova-U1.5-8B-MoT-bf16Aug 24, 20260
  3. 3SenseNova-U1.5-8B-MoT-8bitAug 24, 20260
  4. 4SenseNova-U1.5-8B-MoT-8step-8bitAug 24, 20260
  5. 5SenseNova-U1.5-8B-MoT-8step-4bitAug 24, 20261
  6. 6ltx-2.5-mlx-q8Aug 21, 2026223
  7. 7ltx-2.5-mlx-ditq8Aug 21, 20260
  8. 8Qwen3.8-27B-OptiQ-4bitAug 17, 20268,107
  9. 9mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-MXFP4Aug 16, 2026961
  10. 10mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-8BitAug 16, 20261,333

All models

All tracked models published by mlx-community
ModelDL 30D7D
granite-4.1-3b-mxfp4mlx-community/granite-4.1-3b-mxfp4770—
embeddinggemma-300m-8bitmlx-community/embeddinggemma-300m-8bit764—
NVIDIA-Nemotron-Nano-9B-v2-4bitsmlx-community/nvidia-nemotron-nano-9b-v2-4bits763—
Qwen3.6-35B-A3B-mxfp4mlx-community/qwen3.6-35b-a3b-mxfp4743—
embeddinggemma-300m-bf16mlx-community/embeddinggemma-300m-bf16734—
Nemotron-Cascade-2-30B-A3B-4bitmlx-community/nemotron-cascade-2-30b-a3b-4bit715—
LFM2.5-2.6B-mxfp4mlx-community/lfm2.5-2.6b-mxfp4652—
Devstral-Small-2-24B-Instruct-2512-OptiQ-4bitmlx-community/devstral-small-2-24b-instruct-2512-optiq-4bit641—
whisper-large-v3-turbo-fp16mlx-community/whisper-large-v3-turbo-fp16640—
bge-small-en-v1.5-bf16mlx-community/bge-small-en-v1.5-bf16639—
NemotronLabs-VoiceChat-11B-8bitmlx-community/nemotronlabs-voicechat-11b-8bit634—
VibeVoice-ASR-4bitmlx-community/vibevoice-asr-4bit632—
translategemma-12b-it-4bitmlx-community/translategemma-12b-it-4bit630—
DeepSeek-OCR-2-bf16mlx-community/deepseek-ocr-2-bf16629—
FLUX.2-Klein-4B-3bitmlx-community/flux.2-klein-4b-3bit622—
Qwen-Image-2512-6bitmlx-community/qwen-image-2512-6bit572—
c4ai-command-r-plus-4bitmlx-community/c4ai-command-r-plus-4bit570—
Ornith-1.0-35B-OptiQ-6bitmlx-community/ornith-1.0-35b-optiq-6bit554—
Unlimited-OCR-bf16mlx-community/unlimited-ocr-bf16551—
Mellum2-12B-A2.5B-Instruct-mxfp4mlx-community/mellum2-12b-a2.5b-instruct-mxfp4548—
bge-m3-mlx-4bitmlx-community/bge-m3-mlx-4bit540—
Qwen3-Embedding-4B-mxfp8mlx-community/qwen3-embedding-4b-mxfp8537—
MiniMax-Music3-mxfp4mlx-community/minimax-music3-mxfp4527—
gemma-4-12b-coder-fable5-composer2.5mlx-community/gemma-4-12b-coder-fable5-composer2.5514—
Kimi-VL-A3B-Thinking-8bitmlx-community/kimi-vl-a3b-thinking-8bit500—