Skip to content

Trending AI Today

MiniMaxAI/MiniMax-M3.1-Flash

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

MiniMaxAI/MiniMax-M3.1-Flash is an image text to text model published by MiniMaxAI on Hugging Face. At the collection of October 25, 2026 it was No. 9 on the trending list, with 5,789 downloads in 30 days and 324 likes.

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

Why it is on the list

  • No. 9 by Hugging Face trending score (314)
  • repository created 8 days ago
  • +4 likes since 2026-10-24

5,789downloads in 30 days

324likes

Since October 24, 2026: +0 downloads (30-day figure), +4 likes

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

Open on Hugging Face (opens in a new tab)

Source: Hugging Face public API · updated

Fact sheet

Licence
Other (custom terms) · Read the termsCustom or use-restricted terms (for example OpenRAIL, Llama, Gemma or a vendor licence). Read the licence text before commercial use.
Size
220,490,854,016 parametersAbout 441.0 GB of weights at 16 bits; about 124.0 GB at a typical 4-bit quantisation.
Formats and library
safetensors, transformers
Access
Open download
Created · last changed
·
Downloads, all time
5,789

Most downloaded quantisations

Repositories that declare this model as base

Questions about MiniMax-M3.1-Flash

Why is MiniMaxAI/MiniMax-M3.1-Flash trending?

No. 9 by Hugging Face trending score (314); repository created 8 days ago; +4 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 MiniMax-M3.1-Flash be used commercially?

The repository is tagged with the licence "Other (custom terms)". Custom or use-restricted terms (for example OpenRAIL, Llama, Gemma or a vendor licence). Read the licence text before commercial use. The tag is set by the uploader, so confirm it against the licence file in the repository.

How large is MiniMax-M3.1-Flash?

22B parameters according to the safetensors metadata. Weights alone take about 441 GB at 16 bits per parameter and about 124 GB in a typical 4-bit quantisation, before the memory needed for the context.

Are there quantised versions of MiniMax-M3.1-Flash?

Yes. The most downloaded repositories that declare MiniMaxAI/MiniMax-M3.1-Flash as their base are Baekpica/MiniMax-M3.1-Flash-VQ-GGUF (3,190 downloads in 30 days), webmp3/Sakura-MiniMax-M3.1-Flash-Q3_K_M-GGUF (2,020 downloads in 30 days), LyJonathan/MiniMax-M3.1-Flash-GGUF (1,493 downloads in 30 days).