SmallThinker-21BA3B-Instruct-GGUF
Mungert/SmallThinker-21BA3B-Instruct-GGUF
Tracked by OpenModelStats since September 10, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 374
- Total downloadsCumulative all-time download counter reported by the source platform.
- 4,965
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- 0
- 0% vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 4
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #14312 among tracked Text Generation models.
- #47,714
- 151(down 151 places)this week
- Parameters
- —
- Last source update
- Sep 24, 2025
- MomentumOpenModelStats' composite rising-model signal (0–100): a percentile blend of absolute 7-day download gains, capped percentage growth, and likes gained. See Methodology.
- 4.4
- It moved from #14252 to #14312 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
SmallThinker-21BA3B-Instruct-GGUF is a text generation model published by Mungert. OpenModelStats has tracked the model since Sep 10, 2026, most recently observing it Sep 8, 2026.
- Published
- Aug 2, 2025
- Last updated
- Sep 24, 2025
- Library
- transformers
- License
- apache-2.0
- Task
- Text Generation
- Parameters
- —
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- 0
transformersggufmoetext-generationenarxiv:2507.20984license:apache-2.0endpoints_compatibleregion:usconversational
Publisher
MungertView publisher statistics →Similar models
| Model | DL 30D |
|---|---|
| Qwen3-0.6BQwen | 30.8M |
| gpt2openai-community | 15.5M |
| Qwen3-4BQwen | 10.6M |
| Qwen3-8BQwen | 9.8M |
| Qwen2.5-7B-InstructQwen | 8.1M |
| Qwen2.5-0.5B-InstructQwen | 7.3M |