German consortium releases open 30B model Soofi S

A German AI consortium has released Soofi S, an open large language model with roughly 30 billion parameters, and says it leads benchmark rankings in both English and German. According to The Decoder, the model is a dense architecture rather than a mixture-of-experts design, placing it in the mid-size tier that has become popular for teams that want strong performance without the infrastructure demands of frontier-scale systems.

The headline claim is bilingual strength. Most widely used open models are trained primarily on English data, and their German performance often lags. Soofi S is positioned to close that gap, which matters for European organizations navigating data-residency rules, regulated industries, and users who expect fluent output in their own language.

Why it matters

• A 30B dense model is large enough to be capable yet small enough to self-host, a practical sweet spot for enterprises and researchers.
• Strong German-language results address a persistent weak point in the open ecosystem.
• A consortium model signals continued momentum for sovereign, European-led AI efforts alongside the dominant US and Chinese releases.

The usual caveat applies to any launch that leads with benchmark wins: leaderboard scores are a starting point, not a verdict. Independent evaluation, clarity on the training data and license terms, and real-world testing will determine whether Soofi S earns a lasting place in the crowded field of open mid-size models. For now, it adds a notable European entry worth watching.