architectures · lgai-exaone

EXAONE MoE

Sparse mixture-of-experts backbone behind LG AI Research's K-EXAONE models: 128 experts with 8 routed per token, grouped-query attention over 64 query heads against 8 key/value heads, and sliding-window attention. Declared as model_type `exaone_moe`.

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.

Re-check this yourself → Source → Full record →

What is recorded

Publisher	lgai-exaone
Origin	South Korea
Licence	Apache-2.0

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.