models · minimax

MiniMax M2.5

MiniMax M2.5. 230B, 1M context, 435 tok/s. Arena 1043. Highest throughput in its tier at 435 tok/s. GPQA Diamond 80.2%.

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-2567f54e26676152327d2cae77b05c8a642b70ee4c5a8ec49ede5cb254fbbd047d6
Methodhf-published-sha256

What is recorded

Publisherminimax
OriginRecorded as a covered nation under 10 U.S.C. § 4872(f) — the PRC, Russia, Iran or North Korea. The registry did not record which.
LicenceMiniMax-Open
Publisher’s own licence statementother
Parameters228,703,644,928 (228.7B)
Context window1M
Modalitytext->text
Architectureminimax_m2
Layers62
Hidden size3072
AttentionGQA (48 heads, 8 KV)
Native precisionF8_E4M3
Pulls recorded here230,016
Downloads reported upstream347,133

Reported scores

GPQA Diamond84.8
IFBench71.6
Humanity's Last Exam20.5

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.

Reported to local-ai-registry

From local-ai-registry (MIT), commit 124959d: 9 runs across 3 machines, 0 validated — model revision and runtime pinned, launch accepted — and 9 candidate, their label for useful evidence without a reproducible-launch promise.

Elsewhere in the registry

Registry record as of 2026-08-13. 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.