K2-Think
IFM/K2-Think
Tracked by OpenModelStats since September 2, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 217
- Total downloadsCumulative all-time download counter reported by the source platform.
- 122.1K
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +59(increase)
- 0.1%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 369
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #15313 among tracked Text Generation models.
- #50,171
- 477(down 477 places)this week
- Parameters
- 32.8B
- Last source update
- Nov 19, 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.
- 25.3
- K2-Think gained 59 downloads during the last seven tracked days.
- It moved from #15131 to #15313 among tracked Text Generation models this week.
Downloads over time
Rolling recent-window downloads as reportedLikes over time
Rank among tracked models
Lower is betterOverview
K2-Think is a text generation model published by IFM. OpenModelStats has tracked the model since Sep 2, 2026, most recently observing it Oct 2, 2026.
- Published
- Sep 8, 2025
- Last updated
- Nov 19, 2025
- Library
- transformers
- License
- apache-2.0
- Task
- Text Generation
- Parameters
- 32,763,876,352
- Spaces
- —
- Derivative models
- 1
- Velocity 7D/day
- 8
transformerssafetensorsqwen2text-generationconversationalenarxiv:2509.07604base_model:Qwen/Qwen2.5-32Bbase_model:finetune:Qwen/Qwen2.5-32Blicense:apache-2.0text-generation-inferenceendpoints_compatible
Publisher
IFMView publisher statistics →Derived from Qwen/Qwen2.5-32B (reported by the source; parent not yet tracked).
Model family
Based on base-model relationships reported by the source's metadata.
Derivative models
Similar models
| Model | DL 30D |
|---|---|
| Qwen2.5-32B-InstructQwen | 1.9M |
| Qwen2.5-32B-Instruct-AWQQwen | 1.2M |
| Qwen2.5-Coder-32B-Instruct-AWQQwen | 1.2M |
| Qwen2.5-Coder-32B-InstructQwen | 912K |
| Qwen2.5-32B-Instruct-GPTQ-Int4Qwen | 487.3K |
| DeepSeek-R1-Distill-Qwen-32Bdeepseek-ai | 449.3K |