DeepSeek-V4-Flash-FP8
sgl-project/DeepSeek-V4-Flash-FP8
291B parametersLicense: mit
Tracked by OpenModelStats since September 7, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 279.3K
- Total downloadsCumulative all-time download counter reported by the source platform.
- 1.8M
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +87.1K(increase)
- 5.5%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 15
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads.
- #1,228
- 1(down 1 places)this week
- Parameters
- 291B
- Last source update
- Apr 24, 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.
- 71.4
- DeepSeek-V4-Flash-FP8 gained 87.1K downloads during the last seven tracked days.
Downloads over time
Daily gain between consecutive observationsLikes over time
Rank among tracked models
Lower is betterOverview
DeepSeek-V4-Flash-FP8 is an AI model published by sgl-project. OpenModelStats has tracked the model since Sep 7, 2026, most recently observing it Oct 7, 2026.
- Published
- Apr 24, 2026
- Last updated
- Apr 24, 2026
- Library
- —
- License
- mit
- Task
- —
- Parameters
- 290,962,195,410
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- 12.4K
safetensorsdeepseek_v4deepseek-v4fp8quantizedbase_model:deepseek-ai/DeepSeek-V4-Flashbase_model:quantized:deepseek-ai/DeepSeek-V4-Flashlicense:mitregion:us
Model family
Based on base-model relationships reported by the source's metadata.
Base model
- DeepSeek-V4-Flash995.9K
Sibling models
Similar models
| Model | DL 30D |
|---|---|
| DeepSeek-V4-Flashdeepseek-ai | 995.9K |
| GLM-5.2-504B0xSero | 388 |
| DeepSeek-V4-Flash-Basedeepseek-ai | 167.1K |
| Ling-plusinclusionAI | 409 |
| dots3-note-prevdots-studio | 995 |
| dots3-note-prev-fp8dots-studio | 406 |