Skip to content
Weights Not Walls
Menu

MiniMaxAI

MiniMax-M3.1-Flash

Reviewedaccepts images
Size
426B parametersfrom the GGUF metadata of a conversion, because this repo's own weights are packed: unsloth/MiniMax-M3.1-Flash-GGUF
Licence
custom, read it, MiniMax Community LicenseOur reading, check the licence: A custom licence we have not read for this model: other makers use the same name for different texts. Read the model's own licence file before you use it.Licence text
On the Hub since
17 Oct 2026the date the repo was created
Context length
1M tokensfrom the model's config
Kind
Base model (no base model declared on the Hub)MiniMaxM3SparseForConditionalGeneration
On Hugging Face
MiniMaxAI/MiniMax-M3.1-Flash110k downloads in the last 30 days, 606 likes

Scores

No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.

Claimed by the maker Claimed

The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.

Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.

Run it yourself

file sizes read from the Hub 19 Nov 2026

Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.94 GB, worked out from the model's config (MiniMaxAI/MiniMax-M3.1-Flash), at 16-bit precision. Choose a machine above to see a verdict for each format. Method

GGUF for llama.cpp, Ollama, LM Studio and others

peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF (converted by peasantsmith), 74k downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
IQ1_S86.6 GBfile size, 2 parts88.0 GB86.6 + 0.94 + 0.50
Commands
llama.cpp
llama-server -hf peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ1_S
Download
hf download peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF --include "Maya-XS/MiniMax-M3.1-Flash-Maya-XS-IQ1_S-*-of-00002.gguf" --local-dir MiniMax-M3.1-Flash-Maya-GGUF
IQ2_XXS114.0 GBfile size, 3 parts115.5 GB114.0 + 0.94 + 0.50
Commands
llama.cpp
llama-server -hf peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ2_XXS
Download
hf download peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF --include "Maya-S/MiniMax-M3.1-Flash-Maya-S-IQ2_XXS-*-of-00003.gguf" --local-dir MiniMax-M3.1-Flash-Maya-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLX 3bitmlx-community/MiniMax-M3.1-Flash-Text-3bit173.7 GBfile size175.1 GB173.7 + 0.94 + 0.50Download page
MLX 4bitmlx-community/MiniMax-M3.1-Flash-Text-4bit231.3 GBfile size232.7 GB231.3 + 0.94 + 0.50Download page

Original weights

The maker's own weights are packed into integer tensors, so the safetensors header gives no size we can trust; the repo lists the real file sizes.

hf download MiniMaxAI/MiniMax-M3.1-Flash --local-dir MiniMax-M3.1-Flash
Other conversions (9; sizes not read)

The Hub tags 42 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.

Run it by API

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

12 providers serve this model through the Hugging Face router. Prices are US dollars per million tokens. Precision is what the provider reports; a lower precision than the original weights can change answers. Live first, then cheapest output.

ProviderInOutContextPrecisionTokens/sFirst tokenUptime 24hToolsJSON
Makora$0.15$0.501Mfp41130.5 s99.6%yesyes
Wafer$0.14$0.541Mnvfp4890.7 s99.9%yesyes
DigitalOcean$0.15$0.601Mnot given981.7 s100.0%yesyes
Fireworks$0.15$0.601Mnot given1070.7 s97.4%yesyes
Inferact vLLM$0.15$0.601Mnvfp41450.7 s100.0%yesyes
InferenceNet$0.15$0.60977kfp4591.3 s98.9%yesyes
ModelRun$0.15$0.601Mfp41190.9 s100.0%yesyes
Nebius$0.15$0.601Mfp41431.4 s100.0%yesyes
novita$0.15$0.60977knot given660.9 s?yesno
Parasail$0.15$0.601Mfp81001.1 s100.0%yesyes
SambaNova$0.15$0.601Mnot given201.6 s99.9%yesyes
Together$0.15$0.601Mnot given1190.7 s99.9%yesyes

Through the router, with a Hugging Face token (the router bills your Hugging Face account). Change the name after the colon to pick another provider.

curl https://router.huggingface.co/v1/chat/completions \ -H "Authorization: Bearer $HF_TOKEN" -H "Content-Type: application/json" \ -d '{"model": "MiniMaxAI/MiniMax-M3.1-Flash:makora", "messages": [{"role": "user", "content": "Hello"}]}'

Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.

Planned for this page Not built yet

Try it in private chat
A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
Fine-tune it
Fine-tuning a few base models from this page and publishing the result here.
Creators and earnings
Pages for people who publish fine-tunes and adapters of this model, and what they earn.
Fund and bounties
Bounties for new open models, paid from a public fund. How the fund will work.
Contribute compute
How to give compute to open model work, with Akash.

Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.