architectures · xiaomi

MiMo Architecture (Token-Level RL)

Xiaomi MiMo (Mixed Model) architecture applying token-level process reward modelling and Group Relative Policy Optimization (GRPO) during post-training. Dense decoder-only transformer with specialised math and code reasoning heads. MiMo-V2-Flash at 309B achieves AIME 94.1% via scaled RL fine-tuning.

Verify

What this registry has checked

Quarantine. We hold the publisher’s own published hash for these weights and have recorded it against this entry. We have not downloaded and hashed the weights ourselves, so the hash is the publisher’s claim, not our measurement.

Weight file SHA-256	2b223446ac5d6a3886ff1059543435c801559a5577409a4b598c6949f3d49053

Re-check this yourself → Source → Full record →

What is recorded

Publisher	xiaomi
Origin	Recorded as a covered nation under 10 U.S.C. § 4872(f) — the PRC, Russia, Iran or North Korea. The registry did not record which.
Licence	Apache-2.0
Pulls recorded here	89,749

Elsewhere in the registry

All architectures → Browse with filters → What will run on my hardware? →

Registry record as of 2026-08-14. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.