Skip to content

dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8

Model · Image text to text · edition of October 25, 2026

dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8 is an image text to text model published by dealignai on Hugging Face, a fine-tune of deepseek-ai/DeepSeek-V4.1-Flash-1017. At the collection of October 25, 2026 it was No. 11 on the trending list, with 5,583 downloads in 30 days and 348 likes.

Collected · snapshot shipped with the site build, not a live feed

Why it is on the list

  • No. 11 by Hugging Face trending score (299)
  • repository created 7 days ago
  • +2 likes since 2026-10-24

5,583downloads in 30 days

348likes

Since October 24, 2026: +0 downloads (30-day figure), +2 likes

Positions and counts are Hugging Face’s; we report them and add no score of our own.

Source: Hugging Face public API · updated

Fact sheet

Licence
MIT · Commercial use allowedPermissive licence: commercial use is allowed, with the attribution and notice conditions of the licence.
Size
763,205,315,794 parametersAbout 1526.4 GB of weights at 16 bits; about 429.3 GB at a typical 4-bit quantisation.
Formats and library
safetensors, transformers
Access
Open download
Created · last changed
·
Downloads, all time
5,583

Most downloaded quantisations

Repositories that declare this model as base

Questions about DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8

Why is dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8 trending?

No. 11 by Hugging Face trending score (299); repository created 7 days ago; +2 likes since 2026-10-24. Hugging Face does not publish the formula of its trending score; these are the public figures behind the position.

Can DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8 be used commercially?

The repository is tagged with the licence "MIT". Permissive licence: commercial use is allowed, with the attribution and notice conditions of the licence. The tag is set by the uploader, so confirm it against the licence file in the repository.

How large is DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8?

763B parameters according to the safetensors metadata. Weights alone take about 1526 GB at 16 bits per parameter and about 429 GB in a typical 4-bit quantisation, before the memory needed for the context.

Are there quantised versions of DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8?

Yes. The most downloaded repositories that declare dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8 as their base are Baekpica/DeepSeek-V4.1-Flash-1017-UNCENSORED-VQ-GGUF (521 downloads in 30 days), staccs/DeepSeek-V4.1-Flash-1017-abliterated-dealignai-lecore-vq11cal-GGUF (115 downloads in 30 days).