mlx-community AI Models
Tracked by OpenModelStats since Aug 23, 2026 · View on Hugging Face ↗
- Tracked modelsRepositories from this publisher currently tracked by OpenModelStats.
- 570
- Downloads 30DSum of each tracked model's rolling recent-downloads counter. A sum of repository counters is not a count of unique users.
- 7.9M
- Total downloadsSum of cumulative all-time download counters across tracked repositories.
- 97.3M
- Total likes
- 6,207
- Gained 7DCombined seven-day cumulative-download gains measured by OpenModelStats.
- —
Most downloaded
- 1parakeet-tdt-0.6b-v2May 10, 20252.2M
- 2parakeet-tdt-0.6b-v3Aug 16, 20251.6M
- 3gpt-oss-20b-MXFP4-Q8Mar 19, 2026350.7K
- 4Qwen3-ASR-0.6B-8bitJan 29, 2026186.7K
- 5Kimi-K2.5Jan 27, 2026161.8K
- 6Qwen2.5-Coder-7B-Instruct-4bitSep 18, 2024161.1K
- 7Qwen3-14B-4bitApr 29, 2025137.2K
- 8Devstral-Small-2-24B-Instruct-2512-4bitJul 4, 2026102.8K
- 9Qwen3-30B-A3B-Instruct-2507-4bitAug 6, 202599.3K
- 10whisper-large-v3-turboApr 12, 202695.5K
Recently updated
- 1Octen-Embedding-4B-MLX-4bitAug 24, 20260
- 2SenseNova-U1.5-8B-MoT-bf16Aug 24, 20260
- 3SenseNova-U1.5-8B-MoT-8bitAug 24, 20260
- 4SenseNova-U1.5-8B-MoT-8step-8bitAug 24, 20260
- 5SenseNova-U1.5-8B-MoT-8step-4bitAug 24, 20261
- 6ltx-2.5-mlx-q8Aug 21, 2026223
- 7ltx-2.5-mlx-ditq8Aug 21, 20260
- 8Qwen3.8-27B-OptiQ-4bitAug 17, 20268,107
- 9mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-MXFP4Aug 16, 2026961
- 10mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-8BitAug 16, 20261,333
All models
| Model | DL 30D | 7D |
|---|---|---|
| Qwen3.6-35B-A3B-5bitmlx-community/qwen3.6-35b-a3b-5bit | 1,831 | — |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-mxfp4mlx-community/nvidia-nemotron-3.5-lightning-30b-a3b-mxfp4 | 1,827 | — |
| Qwen3.8-27B-MTP-mxfp4mlx-community/qwen3.8-27b-mtp-mxfp4 | 1,817 | — |
| snac_24khzmlx-community/snac_24khz | 1,811 | — |
| Qwen3-ASR-0.6B-4bitmlx-community/qwen3-asr-0.6b-4bit | 1,807 | — |
| gemma-4-E4B-it-qat-4bitmlx-community/gemma-4-e4b-it-qat-4bit | 1,804 | — |
| Qwen3-0.6B-bf16mlx-community/qwen3-0.6b-bf16 | 1,799 | — |
| Qwen2.5-Coder-3B-Instruct-4bitmlx-community/qwen2.5-coder-3b-instruct-4bit | 1,798 | — |
| Qwen3-235B-A22B-Thinking-2507-4bitmlx-community/qwen3-235b-a22b-thinking-2507-4bit | 1,795 | — |
| Qwen3-VL-32B-Instruct-8bitmlx-community/qwen3-vl-32b-instruct-8bit | 1,792 | — |
| Phi-3.5-mini-instruct-4bitmlx-community/phi-3.5-mini-instruct-4bit | 1,791 | — |
| GLM-4.7-REAP-50-mxfp4mlx-community/glm-4.7-reap-50-mxfp4 | 1,779 | — |
| Kimi-Linear-48B-A3B-Instruct-4bitmlx-community/kimi-linear-48b-a3b-instruct-4bit | 1,777 | — |
| MiniCPM5-1B-OptiQ-4bitmlx-community/minicpm5-1b-optiq-4bit | 1,758 | — |
| Ornith-1.0-9B-OptiQ-4bitmlx-community/ornith-1.0-9b-optiq-4bit | 1,740 | — |
| LFM2.5-2.6B-8bitmlx-community/lfm2.5-2.6b-8bit | 1,730 | — |
| Qwen2.5-VL-7B-Instruct-8bitmlx-community/qwen2.5-vl-7b-instruct-8bit | 1,725 | — |
| Nanbeige4.2-3B-OptiQ-4bitmlx-community/nanbeige4.2-3b-optiq-4bit | 1,717 | — |
| Qwen3.6-27B-bf16mlx-community/qwen3.6-27b-bf16 | 1,716 | — |
| Qwen3-Embedding-8B-mxfp8mlx-community/qwen3-embedding-8b-mxfp8 | 1,709 | — |
| Ornith-1.0-35B-8bitmlx-community/ornith-1.0-35b-8bit | 1,699 | — |
| Muse-Glimmer-30B-6bitmlx-community/muse-glimmer-30b-6bit | 1,681 | — |
| medgemma-4b-it-4bitmlx-community/medgemma-4b-it-4bit | 1,676 | — |
| Qwen3-VL-2B-Instruct-4bitmlx-community/qwen3-vl-2b-instruct-4bit | 1,672 | — |
| Qwen3-ASR-1.7B-bf16mlx-community/qwen3-asr-1.7b-bf16 | 1,651 | — |