architectures · moonshot-ai

Kimi MoE Architecture

Moonshot AI Kimi K2 sparse Mixture-of-Experts architecture. Top-K expert routing with shared expert caching and expert-parallel load balancing. Supports 262K native context via YaRN positional scaling. K2.5 and K2.6 variants achieve >90% GPQA Diamond and >80% SWE-Bench Verified.

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	5ff9bff435a6be344a444b0f47ec7c9044077b0d885ea230bcbfc1c46229dce9

Re-check this yourself → Source → Full record →

What is recorded

Publisher	moonshot-ai
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	155,798

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.