Motif 3 Technical Report: A 314B Parameter Sparse MoE Model

Motif-Technologies · hf · 2026-08-11

Motif Technologies releases the technical report for Motif 3, a decoder-only Mixture-of-Experts (MoE) language model with 314B total parameters and 13.2B activated per token.

Original post →

More from Models

Models channel →