Step-3.7-Flash
stepfun-ai/Step-3.7-Flash
Tracked by OpenModelStats since September 4, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 24.8K
- Total downloadsCumulative all-time download counter reported by the source platform.
- 396.9K
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +6,960(increase)
- 1.8%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 460
- +2 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #671 among tracked Image Text to Text models.
- #5,257
- 13(up 13 places)this week
- Parameters
- 201B
- Last source update
- Jun 3, 2026
- MomentumOpenModelStats' composite rising-model signal (0–100): a percentile blend of absolute 7-day download gains, capped percentage growth, and likes gained. See Methodology.
- 85.2
- Step-3.7-Flash gained 6,960 downloads during the last seven tracked days.
Downloads over time
Rolling recent-window downloads as reportedLikes over time
Rank among tracked models
Lower is betterOverview
Step-3.7-Flash is a image text to text model published by stepfun-ai. OpenModelStats has tracked the model since Sep 4, 2026, most recently observing it Oct 4, 2026.
- Published
- May 23, 2026
- Last updated
- Jun 3, 2026
- Library
- transformers
- License
- apache-2.0
- Task
- Image Text to Text
- Parameters
- 201,365,316,160
- Spaces
- —
- Derivative models
- 4
- Velocity 7D/day
- 994
transformerssafetensorsstep3p7image-text-to-textvision-languagemultimodalmoeconversationalcustom_codeenlicense:apache-2.0eval-results
Model family
Based on base-model relationships reported by the source's metadata.
Derivative models
Similar models
| Model | DL 30D |
|---|---|
| Step-3.7-Flash-FP8stepfun-ai | 5,005 |
| Qwen3.5-397B-A17B-MXFP4-AttnFP8-V2amd | 14K |
| Qwen3.5-397B-A17B-NVFP4amd | 2,348 |
| Qwen3.5-397B-A17B-MXFP4-AttnFP8-V3amd | 1,498 |
| Qwen3.5-397B-A17B-NVFP4AxionML | 381 |
| DeepSeek-v4.1-Flash-EXL3-2.0bpw-Ablit-EngramQ4-SM120-Dual-RTX-Pro-6000satgeze | 357 |