German AI consortium releases Soofi S, an open 30B model that tops benchmarks in both English and German
Ad
Skip to content
The Decoder
AI, Menschen, Wirtschaft
-->
Sign In
Register
Subscribe Now
The Decoder
Opens discord in a new tab<br>Opens LinkedIn in a new tab
German AI consortium releases Soofi S, an open 30B model that tops benchmarks in both English and German
Jonathan Kemper
View the LinkedIn Profile of Jonathan Kemper
Jul 13, 2026
Nano Banana Pro prompted by THE DECODER
Key Points
A German research consortium has released the open-source language model Soofi S, which was trained entirely on Deutsche Telekom's AI cloud infrastructure.
The model uses a resource-efficient hybrid architecture that activates only 3.2 of its 31.6 billion parameters per token, keeping processing speed constant even with very long inputs.
With a strong focus on German training data, Soofi S outperforms other fully open models, such as Olmo 3 32B and Apertus 70B, in benchmarks for German, English, and programming tasks.
Ask about this article…
Search
Update – Jul 15, 2026
Statement on the allegation of overtraining added
Update from July 15, 2026:
After launch, critics argued that Soofi S was heavily "overtrained" by the standards of the classic Chinchilla scaling laws. Google DeepMind published those laws in 2022, describing how to balance model size and training data for a fixed compute budget. The sweet spot they identified was roughly 20 tokens per parameter. Soofi S blows past that ratio. With about 27 trillion tokens and 30 billion parameters, it lands at several hundred to one. Factor in only the 3.2 billion parameters active per token, and the ratio jumps to several thousand to one.
Michael Fromm, part of the project's technical leadership, pushes back on that criticism. He argues those rules don't simply carry over to Mixture-of-Experts (MoE) architectures. "There's new research showing that the old scaling laws from dense models no longer apply to MoE architectures," Fromm said. The reason comes down to how MoE models are built. Individual experts benefit from seeing the same documents, so repeated data in a large, high-quality dataset is less of a problem than it would be with dense models. As a point of comparison, Fromm points to Nvidia, which trained its own models on up to 25 trillion tokens.Ad
Original article from July 13, 2026: Ad<br>DEC_D_Incontent-1
Soofi S is one of the first large language models trained entirely on Deutsche Telekom's Industrial AI Cloud in Munich. The open 30B model uses a lean hybrid architecture and a training mix deliberately weighted toward German.
A German research consortium coordinated by the KI Bundesverband (German AI Association) has released Soofi S 30B-A3B, an open language model that, according to its pretraining report, achieves the highest scores on English and German benchmarks among fully open models, surpassing previous leaders like OLMo 3 32B and Apertus 70B.Ad
Thanks to its hybrid Mamba-Transformer architecture, Soofi S maintains throughput even at very long contexts, while dense models like Apertus 70B and Qwen3 32B drop off sharply. | Image: Soofi<br>A lean architecture built for long contexts
Soofi S is a mixture-of-experts model. It contains 31.6 billion parameters in total but activates only about 3.2 billion per generated token. That puts its compute cost closer to a 3B model than a conventional 30B model. The consortium adopts the architecture of Nvidia's Nemotron 3 Nano without modification, a hybrid design combining Mamba-2 layers with standard attention layers.
The key difference from typical transformers is memory behavior. In conventional models, the KV cache that stores previous tokens for attention computation grows linearly with context length. With long inputs and many parallel requests, reloading that cache becomes a bottleneck. Only 6 of Soofi S's 52 layers maintain such a cache at all.Ad<br>DEC_D_Incontent-2
The practical payoff shows up in generation throughput. At a context length of 40,000 tokens with 32 parallel requests, Soofi S generates roughly eight times more tokens per second per GPU than dense models in the 14 to 24 billion parameter range. While throughput drops significantly for conventional models as context grows, Soofi S stays nearly flat from 4,000 to 256,000 tokens. The only model that shows similar behavior in the measurements is Alibaba's Qwen3.5 35B-A3B, which also uses a hybrid architecture.Ad
A training mix built around German
The consortium processed about 27 trillion tokens in total, split across three phases. In the first phase, the model learns language fundamentals from roughly 20 trillion tokens drawn from a broad mix of web, code, math, and domain-specific texts. A second phase follows with about 6 trillion tokens from higher-quality sources, designed to sharpen the patterns learned earlier. A shorter third phase then extends the context window by training on very long documents of up to...