Qwen3-4B-Think-GRPO-MLX
12384-0ashntoi/Qwen3-4B-Think-GRPO-MLX
Tracked by OpenModelStats since October 3, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 356
- Total downloadsCumulative all-time download counter reported by the source platform.
- 356
- 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. #14845 among tracked Text Generation models.
- #49,344
- 365(down 365 places)this week
- Parameters
- 4B
- Last source update
- Oct 3, 2026
- It moved from #14763 to #14845 among tracked Text Generation models this week.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
Qwen3-4B-Think-GRPO-MLX is a text generation model published by 12384-0ashntoi. OpenModelStats has tracked the model since Oct 3, 2026, most recently observing it Oct 4, 2026.
- Published
- Oct 2, 2026
- Last updated
- Oct 3, 2026
- Library
- mlx
- License
- apache-2.0
- Task
- Text Generation
- Parameters
- 4,022,468,096
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- —
mlxsafetensorsqwen3grporeasoninggsm8ktext-generationconversationalendataset:openai/gsm8kbase_model:Qwen/Qwen3-4B-Instruct-2507base_model:finetune:Qwen/Qwen3-4B-Instruct-2507
Publisher
12384-0ashntoiView publisher statistics →Derived from Qwen/Qwen3-4B-Instruct-2507 (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| Qwen3-4BQwen | 12.3M |
| Qwen3-4B-Instruct-2507Qwen | 3.5M |
| Qwen3-4B-Thinking-2507Qwen | 590.5K |
| Qwen3-4B-BaseQwen | 576.7K |
| Qwen3-4B-AWQQwen | 214.2K |
| qwen3-4b-base-dapo-v4ReliquaryForge | 134.2K |