The publication AI reads — a remote MCP server, nothing to install.Connect your agent →
Model register·nvidia·Conversion

nvidia/DeepSeek-V4.1-Flash-1017-NVFP4

nvidia/DeepSeek-V4.1-Flash-1017-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 664,898,390,994. Architectural context length (max_position_embeddings) is 1,048,576. The listed licence is mit. The Hub repository was created on 30 Oct 2026, which is the release date this register uses.

Primary source: the Hugging Face model card for nvidia/DeepSeek-V4.1-Flash-1017-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.

Organisationnvidia
ReleasedRepo creation date on Hugging Face30 Oct 2026
Last modified30 Oct 2026
ParametersExact, from the safetensors index664.9B 664,898,390,994
Context lengthmax_position_embeddings — architectural maximum, not necessarily served1M 1,048,576
Licencemit
Pipeline / taskpipeline_tag on the Hugging Face model APIimage-text-to-text
Base modelDeclared on the Hub and present on this registerdeepseek-ai/DeepSeek-V4.1-Flash-1017
File formatssafetensors, NVFP4
Librarylibrary_name on the Hugging Face model APIModel Optimizer
Architecturedeepseek_v41
Layers40
Vocabulary129,280
DownloadsAt last check2.9k
Likes147
GatedNo

Lineage

This record names deepseek-ai/DeepSeek-V4.1-Flash-1017 as its base model, and that release is on this register.

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.

The Hugging Face model API lists the library as Model Optimizer.

Load it from huggingface.co/nvidia/DeepSeek-V4.1-Flash-1017-NVFP4. This page does not add install steps that the Hub files do not state.

Agent capabilities

This model publishes no chat template, so there is nothing to inspect. That is not evidence of missing support — many base models and some releases simply ship without one.

Questions this record can answer

When was DeepSeek-V4.1-Flash-1017-NVFP4 released?
The Hugging Face repository was created on 30 Oct 2026, which is the date this register uses.
How many parameters does DeepSeek-V4.1-Flash-1017-NVFP4 have?
The safetensors index gives 664,898,390,994 parameters, shown here as 664.9B. That figure is exact, not rounded.
What is the context length of DeepSeek-V4.1-Flash-1017-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-1017-NVFP4 under?
The Hub card lists mit.
Is DeepSeek-V4.1-Flash-1017-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, libraryName, formats, baseModel. Checked 3 Nov 2026.
  • config.json — contextLength, layers, vocabSize, architecture. Checked 3 Nov 2026.

First recorded 1 Nov 2026, last checked 3 Nov 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-1017-NVFP4. This page is a quantisation or conversion. It is kept for completeness, excluded from the sitemap, and marked noindex.