nvidia/DeepSeek-V4.1-Flash-NVFP4
nvidia/DeepSeek-V4.1-Flash-NVFP4 is a nvidia record on this register. The Hugging Face model API lists the pipeline tag as image-text-to-text. The safetensors index gives an exact parameter count of 763,205,315,794. Architectural context length (max_position_embeddings) is 1,048,576. The listed licence is mit. The Hub repository was created on 16 Sept 2026, which is the release date this register uses.
Primary source: the Hugging Face model card for nvidia/DeepSeek-V4.1-Flash-NVFP4. Fields below come from that card, the Hub model API, and the repository’s own config.json when those files exist. A field we cannot source is omitted rather than guessed.
| Organisation | nvidia |
|---|---|
| ReleasedRepo creation date on Hugging Face | 16 Sept 2026 |
| Last modified | 17 Sept 2026 |
| ParametersExact, from the safetensors index | 763.2B 763,205,315,794 |
| Context lengthmax_position_embeddings — architectural maximum, not necessarily served | 1M 1,048,576 |
| Licence | mit |
| Pipeline / taskpipeline_tag on the Hugging Face model API | image-text-to-text |
| File formats | safetensors, NVFP4 |
| Architecture | deepseek_v41 |
| Layers | 40 |
| Vocabulary | 129,280 |
| DownloadsAt last check | 15.9k |
| Likes | 90 |
| Gated | No |
How to run
Safetensors weights are on the Hugging Face repository. The parameter count on this page came from that index.
The repository name marks this record as NVFP4.
Load it from huggingface.co/nvidia/DeepSeek-V4.1-Flash-NVFP4. This page does not add install steps that the Hub files do not state.
Questions this record can answer
- When was DeepSeek-V4.1-Flash-NVFP4 released?
- The Hugging Face repository was created on 16 Sept 2026, which is the date this register uses.
- How many parameters does DeepSeek-V4.1-Flash-NVFP4 have?
- The safetensors index gives 763,205,315,794 parameters, shown here as 763.2B. That figure is exact, not rounded.
- What is the context length of DeepSeek-V4.1-Flash-NVFP4?
- 1,048,576 tokens. That is max_position_embeddings from the model's own config.json — the architectural maximum, not necessarily the context a provider serves.
- What licence is DeepSeek-V4.1-Flash-NVFP4 under?
- The Hub card lists mit.
- Is DeepSeek-V4.1-Flash-NVFP4 gated?
- No. The Hugging Face model API does not mark this repository as gated.
Where each field came from
- Hugging Face model API — releasedAt, lastModified, downloads, likes, task, license, gated, parameters. Checked 24 Sept 2026.
- config.json — contextLength, layers, vocabSize, architecture. Checked 24 Sept 2026.
First recorded 24 Sept 2026, last checked 24 Sept 2026. This record is compiled automatically from the sources above. Where a field is blank, we could not source it and have not guessed. Canonical repository: huggingface.co/nvidia/DeepSeek-V4.1-Flash-NVFP4. This page is a quantisation or conversion. It is kept for completeness, excluded from the sitemap, and marked noindex.