German consortium releases open 30B model Soofi S
A collaborative European effort ships a dense 30-billion-parameter model that claims top marks on both English and German benchmarks.
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.
Sources
- Visit
German AI consortium releases Soofi S, an open 30B model that tops benchmarks
Hacker News
More from Unknown
All Unknown releases →Kandinsky 6.0 Generates Video and Audio Together
Kandinsky Lab's new foundation models produce synchronized sound and motion from a text prompt, in 3B and 29B sizes.
Liquid AI's LFM2.5-VL-DSpark targets faster VLM inference
The new vision-language model from Liquid AI is tuned for accelerated inference, extending the company's LFM2 line into multimodal territory.
Nari Labs Ships Qwen3-Based TTS and ASR Models
The startup pairs speech synthesis and recognition built on Qwen3, pitching accuracy, low latency, and lower cost.
More in Text / LLM
All Text / LLM →IBM's Granite Switch Treats Models Like Software
A new Apache-2.0 release reframes enterprise LLMs as components you can swap and update in place.
Mistral Large 4 Arrives as a 1T-Parameter MoE
The new flagship pairs a trillion total parameters with 52B active per token and adds vision alongside multilingual text.
Nanbeige 4.3 Arrives as a 33B Bilingual Model
A dense English–Chinese language model lands under Apache 2.0, aimed at teams that want permissive licensing at mid-size scale.
0 comments
No comments yet. Be the first to weigh in.