DeepSeek-V4-Flash-W4A16-FP8
canada-quant/DeepSeek-V4-Flash-W4A16-FP8
Tracked by OpenModelStats since September 7, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 203
- Total downloadsCumulative all-time download counter reported by the source platform.
- 25K
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +34(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.
- 16
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #8440 among tracked Text Generation models.
- #30,316
- 655(down 655 places)this week
- Parameters
- 44.1B
- Last source update
- May 25, 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.
- 22.3
- DeepSeek-V4-Flash-W4A16-FP8 gained 34 downloads during the last seven tracked days.
- It moved from #8274 to #8440 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-W4A16-FP8 is a text generation model published by canada-quant. OpenModelStats has tracked the model since Sep 7, 2026, most recently observing it Oct 6, 2026.
- Published
- May 4, 2026
- Last updated
- May 25, 2026
- Library
- vllm
- License
- mit
- Task
- Text Generation
- Parameters
- 44,099,651,063
- Spaces
- 0
- Derivative models
- —
- Velocity 7D/day
- 5
vllmsafetensorsdeepseek_v4deepseekcompressed-tensorsw4a16gptqfp8mixture-of-expertsmoetext-generationen
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 |
|---|---|
| NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4nvidia | 9,920 |
| DeepSeek-V4-Flash-0731-W4A16-AutoRoundIntel | 183 |
| DeepSeek-V4-Flash-0731-W4A16baicai1145 | 450 |
| llama3-42b-v0chargoddard | 33 |
| DeepSeek-V4-Flash-0731-EXL3-K2-calibrated-v0wrldsuksgo2mars | 1,173 |
| Qwen3.8-Flash-Next-VQ-3.2bpwTheDrainFlorist | 2,421 |