MiMo
Xiaomi's Open Source Model, Born for Reasoning
302 followers
Xiaomi's Open Source Model, Born for Reasoning
302 followers
Open-source (Apache 2.0) LLM series 'born for reasoning.' Pre-trained & RL-tuned models (like the 7B) match o1-mini on math/code. Base/SFT/RL models released.
This is the 4th launch from MiMo. View more
MiMo-V2-Pro & Omni
Launching today
MiMo-V2-Pro and MiMo-V2-Omni are Xiaomi’s new agent foundation models. Pro is built for long-chain coding, tool use, and OpenClaw-style workflows, while Omni adds vision and audio to push the same agentic stack into the real world.
Free Options
Launch Team
Flowtica Scribe
Hi everyone!
I’ve never seen a model family rise this fast.
Last year @MiMo was just starting out. Now it’s the #1 daily model on OpenRouter for @OpenClaw usage. Hunter Alpha was secretly V2-Pro all along, and Healer Alpha was V2-Omni.
In less than a year they went from zero to top-tier agentic performance. With Pro's 1M context for heavy tool-calling and Omni's native ability to simultaneously see, hear, and execute UI actions, Xiaomi is building models strictly designed to act as the brains for real-world agentic workflows.
This is the kind of speed that makes you stop and think — the token race just got a lot more interesting!