OpenModelStats

mlx-community AI Models

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

Tracked models
1,042
Downloads 30D
8.6M
Total downloads
114.4M
Total likes
8,522
Gained 7D
2M

Most downloaded

  1. 1parakeet-tdt-0.6b-v3Aug 16, 20252.3M
  2. 2Qwen3.8-27B-4bitSep 14, 2026800.3K
  3. 3parakeet-tdt-0.6b-v2May 10, 2025718.9K
  4. 4gemma-3-12b-it-4bitMar 19, 2025335.3K
  5. 5whisper-large-v3-turboApr 12, 2026290.5K
  6. 6Qwen2.5-Coder-7B-Instruct-4bitSep 18, 2024255.9K
  7. 7Qwen3-ASR-0.6B-8bitJan 29, 2026217.4K
  8. 8gpt-oss-20b-MXFP4-Q8Mar 19, 2026213.4K
  9. 9whisper-small-mlxApr 12, 2026187.2K
  10. 10Qwen3-8B-4bitApr 28, 2025136.1K

Fastest growing

  1. 1parakeet-tdt-0.6b-v3+402.8K in 7D2.3M
  2. 2gemma-3-12b-it-4bit+208.7K in 7D335.3K
  3. 3parakeet-tdt-0.6b-v2+191K in 7D718.9K
  4. 4whisper-large-v3-turbo+94.7K in 7D290.5K
  5. 5whisper-small-mlx+67.9K in 7D187.2K
  6. 6gpt-oss-20b-MXFP4-Q8+66.1K in 7D213.4K
  7. 7Qwen2.5-Coder-7B-Instruct-4bit+64.4K in 7D255.9K
  8. 8Qwen3-8B-4bit+63.7K in 7D136.1K
  9. 9Qwen3-ASR-0.6B-8bit+49.6K in 7D217.4K
  10. 10Kimi-K2.5+40K in 7D131.9K

Recently updated

  1. 1humanizer-12b-OptiQ-4bitOct 12, 20269
  2. 2SenseNova-U1.5-8B-MoT-8step-v2-4bitOct 11, 202624
  3. 3SenseNova-U1.5-8B-MoT-8step-v2-8bitOct 11, 202625
  4. 4SenseNova-U1.5-8B-MoT-8step-4bitOct 11, 2026181
  5. 5SenseNova-U1.5-8B-MoT-8step-8bitOct 11, 202689
  6. 6Mellum2.1-12B-A2.5B-Thinking-6bitOct 11, 202697
  7. 7d1a-e2b-8bitOct 11, 20267
  8. 8d1a-e4b-8bitOct 11, 20268
  9. 9Qwen3.5-0.8B-decisionOct 11, 2026260
  10. 10gemma-4-e2b-it-OptiQ-4bit-decisionOct 11, 202681

All models

All tracked models published by mlx-community
ModelDL 30D7D
Qwen2-VL-2B-Instruct-4bitmlx-community/qwen2-vl-2b-instruct-4bit20.1K+5,856
Ministral-3-3B-Instruct-2512-4bitmlx-community/ministral-3-3b-instruct-2512-4bit19.2K+4,716
Qwen2.5-VL-7B-Instruct-4bitmlx-community/qwen2.5-vl-7b-instruct-4bit18.3K+4,456
gemma-4-26B-A4B-it-qat-OptiQ-4bitmlx-community/gemma-4-26b-a4b-it-qat-optiq-4bit18.3K+2,519
Qwen3.8-27B-MTP-4bitmlx-community/qwen3.8-27b-mtp-4bit18.2K+5,797
Llama-3.1-8B-Instruct-4bitmlx-community/llama-3.1-8b-instruct-4bit18.1K+12.6K
whisper-tinymlx-community/whisper-tiny17.8K+2,760
nomicai-modernbert-embed-base-bf16mlx-community/nomicai-modernbert-embed-base-bf1617.4K+8,624
Qwen3-TTS-12Hz-1.7B-Base-bf16mlx-community/qwen3-tts-12hz-1.7b-base-bf1617.1K+3,403
Qwen3.5-9B-4bitmlx-community/qwen3.5-9b-4bit16.7K+3,221
Qwen2.5-7B-Instruct-4bitmlx-community/qwen2.5-7b-instruct-4bit16.5K+4,061
Qwen2.5-1.5B-Instruct-4bitmlx-community/qwen2.5-1.5b-instruct-4bit16.5K+5,321
Qwen3.8-27B-Uncensored-OptiQ-4bitmlx-community/qwen3.8-27b-uncensored-optiq-4bit16.1K+4,318
Qwen3-1.7B-4bitmlx-community/qwen3-1.7b-4bit15.7K+3,886
gemma-4-E4B-it-qat-mobilemlx-community/gemma-4-e4b-it-qat-mobile15.7K+4,311
gemma-3-12b-it-bf16mlx-community/gemma-3-12b-it-bf1615.3K+13K
Qwen3-30B-A3B-Instruct-2507-4bitmlx-community/qwen3-30b-a3b-instruct-2507-4bit14.2K+3,791
gemma-4-26b-a4b-it-4bitmlx-community/gemma-4-26b-a4b-it-4bit14K+2,808
llava-v1.6-mistral-7b-4bitmlx-community/llava-v1.6-mistral-7b-4bit13.9K+3,095
llava-1.5-7b-4bitmlx-community/llava-1.5-7b-4bit13.7K+3,057
whisper-base-mlxmlx-community/whisper-base-mlx13.5K+1,833
Qwen2.5-3B-Instruct-4bitmlx-community/qwen2.5-3b-instruct-4bit13.3K+3,370
DeepSeek-V4-Flash-4bitmlx-community/deepseek-v4-flash-4bit13.1K+3,758
Qwen3.5-2B-MLX-4bitmlx-community/qwen3.5-2b-mlx-4bit11.6K+3,343
whisper-large-v3-turbo-q4mlx-community/whisper-large-v3-turbo-q411.1K+2,938