usermma AI Models
Tracked by OpenModelStats since Aug 23, 2026 · View on Hugging Face ↗
- Tracked modelsRepositories from this publisher currently tracked by OpenModelStats.
- 20
- Downloads 30DSum of each tracked model's rolling recent-downloads counter. A sum of repository counters is not a count of unique users.
- 6,500
- Total downloadsSum of cumulative all-time download counters across tracked repositories.
- 22.7K
- Total likes
- 21
- Gained 7DCombined seven-day cumulative-download gains measured by OpenModelStats.
- 993
Most downloaded
- 1TwIL-LM3-mlx-8BitAug 15, 20261,702
- 2Quark-270m-Instruct-i1-GGUFSep 3, 2026953
- 3Quark-270m-Base-i1-GGUFSep 3, 2026874
- 4Qwen3.8-Queen-27B-mlx-2BitAug 14, 2026559
- 5Quark-270m-Instruct-GGUFSep 3, 2026472
- 6TwIL-LM3-mlx-fp16Aug 15, 2026312
- 7Huihui-MiniCPM5-1B-abliterated-mlx-2BitJun 3, 2026294
- 8Qwable-9B-Claude-Fable-5-mlx-8BitJun 16, 2026214
- 9Vibe-Coding-Claude-Fable-5-mlx-8BitJun 16, 2026190
- 10Quark-270m-Base-GGUFSep 3, 2026165
Fastest growing
- 1TwIL-LM3-mlx-8Bit+861 in 7D1,702
- 2Quark-270m-Instruct-GGUF+0 in 7D472
- 3Quark-270m-Instruct-i1-GGUF+0 in 7D953
- 4TwIL-LM3-mlx-fp16+0 in 7D312
- 5Quark-270m-Base-i1-GGUF+0 in 7D874
- 6Qwen3.8-Queen-27B-mlx-2Bit+0 in 7D559
Recently updated
- 1Quark-270m-Base-GGUFSep 3, 2026165
- 2Quark-270m-Base-i1-GGUFSep 3, 2026874
- 3Quark-270m-Instruct-i1-GGUFSep 3, 2026953
- 4Quark-270m-Instruct-GGUFSep 3, 2026472
- 5TwIL-LM3-mlx-8BitAug 15, 20261,702
- 6TwIL-LM3-mlx-fp16Aug 15, 2026312
- 7Qwen3.8-Queen-27B-mlx-2BitAug 14, 2026559
- 8DeepHat-V1-7B-Heretic-Abliterated-mlx-8BitJul 10, 2026105
- 9Vibe-Coding-Claude-Fable-5-mlx-8BitJun 16, 2026190
- 10Vibe-Coding-Claude-Fable-5-mlx-6BitJun 16, 202669
All models
| Model | DL 30D | 7D |
|---|---|---|
| TwIL-LM3-mlx-8Bitusermma/twil-lm3-mlx-8bit | 1,702 | +861 |
| Quark-270m-Instruct-i1-GGUFusermma/quark-270m-instruct-i1-gguf | 953 | +0 |
| Quark-270m-Base-i1-GGUFusermma/quark-270m-base-i1-gguf | 874 | +0 |
| Qwen3.8-Queen-27B-mlx-2Bitusermma/qwen3.8-queen-27b-mlx-2bit | 559 | +0 |
| Quark-270m-Instruct-GGUFusermma/quark-270m-instruct-gguf | 472 | +0 |
| TwIL-LM3-mlx-fp16usermma/twil-lm3-mlx-fp16 | 312 | +0 |
| Huihui-MiniCPM5-1B-abliterated-mlx-2Bitusermma/huihui-minicpm5-1b-abliterated-mlx-2bit | 294 | +0 |
| Qwable-9B-Claude-Fable-5-mlx-8Bitusermma/qwable-9b-claude-fable-5-mlx-8bit | 214 | — |
| Vibe-Coding-Claude-Fable-5-mlx-8Bitusermma/vibe-coding-claude-fable-5-mlx-8bit | 190 | +44 |
| Quark-270m-Base-GGUFusermma/quark-270m-base-gguf | 165 | +0 |
| MiniCPM5-1B-mlx-fp16usermma/minicpm5-1b-mlx-fp16 | 134 | — |
| DeepHat-V1-7B-Heretic-Abliterated-mlx-8Bitusermma/deephat-v1-7b-heretic-abliterated-mlx-8bit | 105 | +12 |
| LFM2.5-1.2B-MEGABRAIN-Thinking-Claude-Polaris-Deepseek-GLM-abliterated-failspyusermma/lfm2.5-1.2b-megabrain-thinking-claude-polaris-deepseek-glm-abliterated-failspy | 102 | — |
| Huihui-LFM2.5-8B-A1B-abliterated-mlx-2Bitusermma/huihui-lfm2.5-8b-a1b-abliterated-mlx-2bit | 91 | +0 |
| Huihui-LFM2.5-8B-A1B-abliterated-mlx-4Bitusermma/huihui-lfm2.5-8b-a1b-abliterated-mlx-4bit | 81 | — |
| Vibe-Coding-Claude-Fable-5-mlx-6Bitusermma/vibe-coding-claude-fable-5-mlx-6bit | 69 | +26 |
| Vibe-Coding-Claude-Fable-5-mlx-fp16usermma/vibe-coding-claude-fable-5-mlx-fp16 | 56 | +10 |
| Vibe-Coding-Claude-Fable-5-mlx-4Bitusermma/vibe-coding-claude-fable-5-mlx-4bit | 54 | +13 |
| FastContext-1.0-4B-RL-mlx-fp16usermma/fastcontext-1.0-4b-rl-mlx-fp16 | 45 | +13 |
| FastContext-1.0-4B-SFT-mlx-8Bitusermma/fastcontext-1.0-4b-sft-mlx-8bit | 35 | +14 |