models · xiaomi

MiMo-V2-Flash

Xiaomi MiMo-V2-Flash. 309B. Arena 793. GPQA Diamond 83.7%, AIME 94.1%. Efficient flash-inference variant of the MiMo-V2 series.

Compare 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	374e63be8f92083e357da700bf29ee0c1ad708347595713c4ffe04bb3c1697b6
Method	hf-published-sha256

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
Publisher’s own licence statement	mit
Parameters	8,306,217,216 (8.31B)
Context window	128K
Architecture	qwen2_5_vl
Layers	36
Hidden size	4096
Attention	GQA (32 heads, 8 KV)
Native precision	BF16
Pulls recorded here	160,012
Downloads reported upstream	1,128

Reported scores

GPQA Diamond	83.5
IFBench	71.8
Humanity's Last Exam	22.1

Reported by a third party and recorded here, not re-run by us. Source: artificialanalysis.ai/api/v2.

Measured on real hardware

None of these runs are ours. Each figure is the reporter’s, linked to their own evidence, under their own trust label. The number shown is single-stream decode — one user, concurrency 1 — because aggregate throughput across many users is a different quantity and reads as far faster than anyone will see.

Measured by local.ai

Hardware	Build measured	Decode @ 8K	Memory @ 8K	Decode mode
MacBook Pro M5 Max 128GB · 40-core GPU	UD-IQ2_M	57.2 tok/s	111.7 GB	ordinary
MacBook Pro M5 Max 128GB · 40-core GPU	UD-IQ2_XXS	56.1 tok/s	106.6 GB	ordinary
Mac Studio M3 Ultra 96GB · 80-core GPU	UD-IQ2_XXS	50.7 tok/s	51.2 GB	ordinary
Mac Studio M3 Ultra 96GB · 80-core GPU	UD-IQ2_M	50.4 tok/s	51.2 GB	ordinary
MacBook Pro M4 Max 128GB · 40-core GPU	UD-IQ2_M	39.0 tok/s	111.1 GB	ordinary
NVIDIA DGX Spark 128GB	UD-IQ2_XXS	24.8 tok/s	108.0 GB	ordinary
NVIDIA DGX Spark 128GB	UD-IQ2_M	24.3 tok/s	113.1 GB	ordinary

Measured by local.ai, not by us: 7 runs. Each names its engine pinned by image digest and the exact serve command, in the full record.

Elsewhere in the registry

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

Registry record as of 2026-06-11. 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.