Skip to content
Hacker News front page

German consortium releases Soofi S, a 30B open model topping German and English benchmarks

German AI consortium releases Soofi S, an open 30B model that tops benchmarks

Soofi S is a 30B open model trained entirely on Deutsche Telekom's Munich cloud by a German AI consortium. It uses a hybrid Mamba-Transformer MoE design, activating only 3.2B parameters per token, so throughput stays nearly flat even at 256K context. The training mix deliberately favors German, and it beats Olmo 3 32B and Apertus 70B on German, English, and coding benchmarks. Critics called it overtrained under Chinchilla scaling laws; the project's tech lead counters that those laws don't hold for MoE and notes Nvidia trained on up to 25T tokens.

Why it matters: Germany's open-source Soofi S holds inference cost down with 31.6B total and 3.2B active parameters, beating Olmo 3 32B and Apertus 70B on German, English and coding benchmarks.

Read the original ↗Export Markdown