nvidia/DeepSeek-V4-Flash-NVFP4 download history
nvidia/DeepSeek-V4-Flash-NVFP4 is a 290.9B-parameter text generation model by nvidia. In the last 30 days it was downloaded 106,430 times (41,330 in the last 7 days), and 2,068,958 times in total.
It ranks #2,234 on the Hub by monthly downloads and #455 among text generation models.
It has 119 likes.
It is a quantization of deepseek-ai/DeepSeek-V4-Flash.
2 models build on DeepSeek-V4-Flash-NVFP4: 1 quantized, 0 fine-tuned, 1 adapters and 0 merges. Together with the original they were downloaded 106,488 times in the last 30 days. See the DeepSeek-V4-Flash-NVFP4 galaxy.
Most downloaded derivatives
- appmana/deepseek-v4-nvfp4-fp8 (quantized), 32 downloads in 30 days
- nmitchko/deepseek-v4-Flash-CoLaR (adapter), 26 downloads in 30 days
Downloads by month
Downloads in the 30 days up to the end of each month, and the change from the month before.
| Month | Downloads | Change |
|---|---|---|
| Up to 2026-11-18 | 106,430 | +635% |
| October 2026 | 14,479 | -36% |
| September 2026 | 22,779 | -92% |
| August 2026 | 283,732 | -78% |
| July 2026 | 1,287,622 | +340% |
Its busiest 30 days so far ended on 2026-07-25, with 1,385,108 downloads.
Open nvidia/DeepSeek-V4-Flash-NVFP4 on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.