Qwen3-Coder-16B-A3B-KREAP-MLX
RAS-LAB/Qwen3-Coder-16B-A3B-KREAP-MLX
Tracked by OpenModelStats since September 28, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 1,523
- Total downloadsCumulative all-time download counter reported by the source platform.
- 1,973
- 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.
- 0
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads.
- —
- –this week
- Parameters
- 16B
- Last source update
- Sep 28, 2026
Downloads over time
Rolling recent-window downloads as reportedLikes over time
Rank among tracked models
Lower is betterNot enough tracked history yet for a chart.
OpenModelStats began tracking this model on 2026-09-28. Charts appear as daily observations accumulate.
Overview
Qwen3-Coder-16B-A3B-KREAP-MLX is a text generation model published by RAS-LAB. OpenModelStats has tracked the model since Sep 28, 2026, most recently observing it Oct 27, 2026.
- Published
- Jul 22, 2026
- Last updated
- Sep 28, 2026
- Library
- mlx
- License
- apache-2.0
- Task
- Text Generation
- Parameters
- 16,030,316,544
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- —
mlxsafetensorsqwen3_moemoepruningreapk-reapkoreanexpert-pruningtext-generationconversationalko
Publisher
RAS-LABView publisher statistics →Derived from Qwen/Qwen3-Coder-30B-A3B-Instruct (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| Moonlight-16B-A3B-Instructmoonshotai | 35.9K |
| Moonlight-16B-A3Bmoonshotai | 20.4K |
| starchat2-15b-v0.1HuggingFaceH4 | 189 |
| starcoder2-15bbigcode | 14.4K |
| starcoder2-15b-instruct-v0.1bigcode | 1,309 |
| granite-4.2-30b-mxfp4ibm-granite | 1,054 |