DeepSeek-V4-Flash-MXFP4
amd/DeepSeek-V4-Flash-MXFP4
Tracked by OpenModelStats since October 1, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 4,406
- Total downloadsCumulative all-time download counter reported by the source platform.
- 6,122
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +283(increase)
- 15.6%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 1
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #3241 among tracked Text Generation models.
- #12,728
- 6(down 6 places)this week
- Parameters
- 149B
- Last source update
- Sep 17, 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.
- 52.8
- DeepSeek-V4-Flash-MXFP4 gained 283 downloads during the last seven tracked days.
- It moved from #3238 to #3241 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
DeepSeek-V4-Flash-MXFP4 is a text generation model published by amd. OpenModelStats has tracked the model since Oct 1, 2026, most recently observing it 31h ago.
- Published
- May 6, 2026
- Last updated
- Sep 17, 2026
- Library
- transformers
- License
- mit
- Task
- Text Generation
- Parameters
- 148,669,630,418
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- 40
transformerssafetensorsdeepseek_v4text-generationocp-mxquantizationamd-quarkmoedeepseekbase_model:deepseek-ai/DeepSeek-V4-Flashbase_model:quantized:deepseek-ai/DeepSeek-V4-Flashlicense:mit
Publisher
amdView publisher statistics →Model family
Based on base-model relationships reported by the source's metadata.
Base model
- DeepSeek-V4-Flash966.5K
Sibling models
Similar models
| Model | DL 30D |
|---|---|
| DeepSeek-v4-FableChunjiang-Intelligence | 380 |
| DeepSeek-V4-Flash-0731-reap-150bpuwaer | 2,286 |
| GLM-5.3-UNCENSORED-EXL3-3.0bpwInfatoshi | 1,903 |
| GLM-5.3-EXL3-3.0bpw0xSero | 414 |
| DeepSeek-V4-Flash-0731-NVFP4RedHatAI | 605 |
| DeepSeek-V4-Flash-0731-NVFP4-FP8-BLOCKRedHatAI | 110 |