A faster, lighter model from the same family as Xiaomi's flagship
Made by Xiaomi MiMo
View profile on Hugging Face (opens in a new tab)MiMo-V2.6-Flash-RL is a lighter, faster checkpoint in Xiaomi's MiMo-V2.6 family, trained with the same underlying approach as the larger Pro-RL model — text, image, video and audio in one model, long context for agent work, and reinforcement learning mixed across coding, general-agent, visual and cybersecurity tasks rather than trained separately for each.
It is positioned as the quicker, cheaper option in the family for situations where the largest checkpoint's cost or latency is not worth it.
You could use it to…
- Get faster, cheaper responses from the MiMo-V2.6 family
- Run one model across coding, agent and vision tasks
- Trade some capability for lower latency in production
Can I use this?
You'll need A GPU and a serving framework such as SGLang · Setup needed
Worth knowing As the smaller, faster sibling in the family it trades some capability for speed compared to the Pro-RL checkpoint, and its performance figures are the creator's own reported results from the same technical report. MIT licence. BuildTube has not run or verified this model.
Why it's here
Not trending this week
Last seen on the Hugging Face trending list on 28 September 2026. It stays on BuildTube so you can still find it.
- 541 people have liked it on Hugging Face.
- It was downloaded 53,382 times in the last 30 days.
Numbers checked on 6 October 2026; not refreshed since.
Behind it
See the code on Hugging FaceBuildTube has not run or verified this project. Everything above is written from what the creator published.
Made this?