Soofi S releases a 30B-A3B open Mamba-MoE model trained on 27T tokens

_ScottCondron · x · 2026-07-23

The post announces the Soofi S pretraining tech report, describing a 30B-A3B mixture-of-experts hybrid Mamba model trained on about 27T tokens with intentionally up-weighted German.

Key claims from the report:

The post is basically celebrating how unusually open the whole training stack is, not just the model weights.

Related event: Soofi S Releases 30B Hybrid Mamba Open-Source Model(2 posts)→

Original post →

More from Models

Models channel →