Skip to content
Weights Not Walls
Menu

XiaomiMiMo

MiMo-V2.6-Flash-RL

Reviewed
Size
309B parametersfrom the GGUF metadata of a conversion, because this repo's own weights are packed: vultr/MiMo-V2.6-Flash-RL-GGUF
Licence
unknown, MIT LicenseOur reading, check the licence: You can use, change and redistribute the model for any purpose, including commercially. Keep the copyright notice and the licence text with copies. You do not have to share your changes.
On the Hub since
21 Sep 2026the date the repo was created
Context length
1M tokensfrom the model's config
Kind
Base model (no base model declared on the Hub)MiMoV2ForCausalLM
On Hugging Face
XiaomiMiMo/MiMo-V2.6-Flash-RL42k downloads in the last 30 days, 599 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: 1.1 GB, worked out from the model's config (XiaomiMiMo/MiMo-V2.6-Flash-RL), 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

vultr/MiMo-V2.6-Flash-RL-GGUF (converted by vultr), 20k downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
IQ3_S136.7 GBfile size138.3 GB136.7 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf vultr/MiMo-V2.6-Flash-RL-GGUF:IQ3_S
Ollama
ollama run hf.co/vultr/MiMo-V2.6-Flash-RL-GGUF:IQ3_S
Download
hf download vultr/MiMo-V2.6-Flash-RL-GGUF --include "MiMo-V2.6-Flash-RL-IQ3_S.gguf" --local-dir MiMo-V2.6-Flash-RL-GGUF
IQ3_M138.4 GBfile size140.0 GB138.4 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf vultr/MiMo-V2.6-Flash-RL-GGUF:IQ3_M
Ollama
ollama run hf.co/vultr/MiMo-V2.6-Flash-RL-GGUF:IQ3_M
Download
hf download vultr/MiMo-V2.6-Flash-RL-GGUF --include "MiMo-V2.6-Flash-RL-IQ3_M.gguf" --local-dir MiMo-V2.6-Flash-RL-GGUF
MXFP4155.9 GBfile size, 2 parts157.5 GB155.9 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf vultr/MiMo-V2.6-Flash-RL-GGUF:MXFP4
Download
hf download vultr/MiMo-V2.6-Flash-RL-GGUF --include "MiMo-V2.6-Flash-RL-MXFP4-*-of-00002.gguf" --local-dir MiMo-V2.6-Flash-RL-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLX mxfp4mlx-community/MiMo-V2.6-Flash-RL-mxfp4-q8155.8 GBfile size157.4 GB155.8 + 1.1 + 0.50Download page
MLX 4bitTensorFold/MiMo-V2.6-Flash-RL-MLX-4bit-MTP159.9 GBfile size161.5 GB159.9 + 1.1 + 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 XiaomiMiMo/MiMo-V2.6-Flash-RL --local-dir MiMo-V2.6-Flash-RL
Other conversions (10; sizes not read)

The Hub tags 39 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

4 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
Cohere$0.14$0.281Mfp8960.6 s99.2%yesyes
DeepInfra$0.14$0.281Mfp8373.4 s98.1%yesyes
novita$0.14$0.281Mnot given222.5 s?yesno
Makora$0.20$0.401Mfp8451.4 s97.0%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": "XiaomiMiMo/MiMo-V2.6-Flash-RL:cohere", "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.