Korean Company Motif Releases 314B MoE Open-Weight Model, Rivals DeepSeek V4 Pro

eliebakouch · x · 2026-07-21

Korean company Motif releases Motif 2.6B tech report, a 13B active 314B total MoE model, performing on par with Minimax M3 and DeepSeek V4 Pro. It features differential attention (GDLA), per-expert activation function polynorm, modified mHC. Trained on 2.5T tokens with data mixture scheduling and WSD. Fine-tuning uses EvolKit and dataset fusion.

Related event: Korea's Motif Releases Motif-3 Beta with 314B Parameters on Hugging Face(4 posts)→

Original post →

More from Models

Models channel →