models · moonshot-ai

Kimi K2

Kimi K2 — catalogued from third-party evaluation data; no weights held by Sovereign Frontier.

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.

Method	hf-published-sha256

Re-check this yourself → Source → Full record →

What is recorded

Publisher	moonshot-ai
Origin	China
Licence	Kimi-Open
Publisher’s own licence statement	other
Parameters	1,026,408,235,864 (1026.4B)
Context window	131,072 tokens
Modality	text->text
Architecture	kimi_k2
Layers	61
Hidden size	7168
Attention	MLA (64 heads, 64 KV)
Native precision	F8_E4M3
Downloads reported upstream	162,957

Reported scores

MMLU-Pro	82.4
GPQA Diamond	76.6
AIME 2025	57
MATH-500	97.1
LiveCodeBench	55.6
IFBench	41.5
Humanity's Last Exam	7.4

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

Elsewhere in the registry

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

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.