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, 2026353.7K
  4. 4Qwen3-ASR-0.6B-8bitJan 29, 2026183.8K
  5. 5Kimi-K2.5Jan 27, 2026162.6K
  6. 6Qwen2.5-Coder-7B-Instruct-4bitSep 18, 2024153.8K
  7. 7Qwen3-14B-4bitApr 29, 2025139.3K
  8. 8Devstral-Small-2-24B-Instruct-2512-4bitJul 4, 2026103.2K
  9. 9Qwen3-30B-A3B-Instruct-2507-4bitAug 6, 202598.4K
  10. 10whisper-large-v3-turboApr 12, 202694.6K

Recently updated

  1. 1SenseNova-U1.5-8B-MoT-bf16Aug 24, 20260
  2. 2SenseNova-U1.5-8B-MoT-8bitAug 24, 20260
  3. 3SenseNova-U1.5-8B-MoT-8step-8bitAug 24, 20260
  4. 4SenseNova-U1.5-8B-MoT-8step-4bitAug 24, 20260
  5. 5ltx-2.5-mlx-q8Aug 21, 2026120
  6. 6ltx-2.5-mlx-ditq8Aug 21, 20260
  7. 7Qwen3.8-27B-OptiQ-4bitAug 17, 20267,610
  8. 8mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-MXFP4Aug 16, 2026997
  9. 9mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-8BitAug 16, 20261,351
  10. 10MiniMax-Music3-mxfp4Aug 16, 2026483

All models

All tracked models published by mlx-community
ModelDL 30D7D
Qwen3.6-35B-A3B-4bitmlx-community/qwen3.6-35b-a3b-4bit32K—
Muse-Glimmer-30B-4bitmlx-community/muse-glimmer-30b-4bit31.3K—
Qwen2.5-3B-Instruct-4bitmlx-community/qwen2.5-3b-instruct-4bit31K—
gemma-4-12B-it-qat-4bitmlx-community/gemma-4-12b-it-qat-4bit30.7K—
Qwen3.5-4B-MLX-4bitmlx-community/qwen3.5-4b-mlx-4bit29K—
whisper-large-v3-mlxmlx-community/whisper-large-v3-mlx28.9K—
gemma-3-27b-it-qat-4bitmlx-community/gemma-3-27b-it-qat-4bit27.4K—
Qwen3.5-9B-MLX-4bitmlx-community/qwen3.5-9b-mlx-4bit27.2K—
orpheus-3b-0.1-ft-bf16mlx-community/orpheus-3b-0.1-ft-bf1627K—
gemma-3-12b-it-qat-4bitmlx-community/gemma-3-12b-it-qat-4bit26.8K—
Llama-3.2-3B-Instruct-4bitmlx-community/llama-3.2-3b-instruct-4bit24.5K—
Qwen3.6-27B-4bitmlx-community/qwen3.6-27b-4bit23.8K—
Qwen2.5-1.5B-Instruct-4bitmlx-community/qwen2.5-1.5b-instruct-4bit22.7K—
Mistral-7B-Instruct-v0.3-4bitmlx-community/mistral-7b-instruct-v0.3-4bit22.5K—
Qwen3.6-35B-A3B-8bitmlx-community/qwen3.6-35b-a3b-8bit20.9K—
Qwen2.5-0.5B-Instruct-4bitmlx-community/qwen2.5-0.5b-instruct-4bit20.3K—
gemma-2-9b-it-4bitmlx-community/gemma-2-9b-it-4bit20K—
DeepSeek-V4-Flash-2bit-DQmlx-community/deepseek-v4-flash-2bit-dq20K—
Qwen3-VL-4B-Instruct-4bitmlx-community/qwen3-vl-4b-instruct-4bit19.7K—
Qwen2.5-7B-Instruct-4bitmlx-community/qwen2.5-7b-instruct-4bit17.9K—
Qwen3-4B-4bitmlx-community/qwen3-4b-4bit17.7K—
DeepSeek-V4-Flash-4bitmlx-community/deepseek-v4-flash-4bit17.2K—
Meta-Llama-3.1-8B-Instruct-4bitmlx-community/meta-llama-3.1-8b-instruct-4bit17.1K—
Qwen3.8-27B-MTP-4bitmlx-community/qwen3.8-27b-mtp-4bit17K—
Ministral-3-3B-Instruct-2512-4bitmlx-community/ministral-3-3b-instruct-2512-4bit16.9K—