Qwen3.8-27B-MLX-4bit
TensorFold/Qwen3.8-27B-MLX-4bit
Tracked by OpenModelStats since October 2, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 2,815
- Total downloadsCumulative all-time download counter reported by the source platform.
- 4,219
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- —
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 1
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #1743 among tracked Image Text to Text models.
- #16,918
- 786(up 786 places)this week
- Parameters
- 27.4B
- Last source update
- Oct 1, 2026
- It moved from #1803 to #1743 among tracked Image Text to Text models this week.
Downloads over time
Rolling recent-window downloads as reportedLikes over time
Rank among tracked models
Lower is betterOverview
Qwen3.8-27B-MLX-4bit is a image text to text model published by TensorFold. OpenModelStats has tracked the model since Oct 2, 2026, most recently observing it 4h ago.
- Published
- Aug 14, 2026
- Last updated
- Oct 1, 2026
- Library
- mlx
- License
- apache-2.0
- Task
- Image Text to Text
- Parameters
- 27,356,728,560
- Spaces
- 1
- Derivative models
- —
- Velocity 7D/day
- —
mlxsafetensorsqwen3_5mlx-vlmomlxqwenqwen3.8multimodalquantizedapple-silicon4-bitimage-text-to-text
Model family
Based on base-model relationships reported by the source's metadata.
Base model
- Qwen3.8-27B6.8M
Similar models
| Model | DL 30D |
|---|---|
| Qwen3.8-27B-MLX-4bitlmstudio-community | 4.2M |
| Qwen3.8-27B-MLX-8bitlmstudio-community | 4M |
| Qwen3.8-27B-MLX-6bitlmstudio-community | 4M |
| Qwen3.8-27B-MLX-5bitlmstudio-community | 4M |
| Qwen3.8-27B-4bitmlx-community | 411.9K |
| Qwen3.8-27B-W4A16-AWQphilbert440 | 316.3K |