{"id":541533,"date":"2026-06-24T10:37:14","date_gmt":"2026-06-24T08:37:14","guid":{"rendered":"https:\/\/silicon-saxony.de\/fraunhofer-iais-soofi-a-model-for-industrial-ai-in-europe\/"},"modified":"2026-06-24T10:37:14","modified_gmt":"2026-06-24T08:37:14","slug":"fraunhofer-iais-soofi-a-model-for-industrial-ai-in-europe","status":"publish","type":"post","link":"https:\/\/silicon-saxony.de\/en\/fraunhofer-iais-soofi-a-model-for-industrial-ai-in-europe\/","title":{"rendered":"Fraunhofer IAIS: Soofi \u2013 A Model for Industrial AI in Europe"},"content":{"rendered":"

<\/p>\n

Soofi S marks the start of the project\u2019s first release phase. The model is intended for use particularly in scenarios where organizations want to operate AI applications in a transparent and customizable manner on their own or sovereign infrastructure\u2014such as in industrial processes, the analysis of extensive technical and regulatory documents, code generation, or agent-based AI systems. Trained from scratch on 27 trillion (27T) tokens, Soofi S\u2014a 30-billion-parameter (30B A3B) mixture-of-experts model\u2014combines high throughput with low energy consumption thanks to its hybrid Mamba-Transformer architecture.<\/p>\n

Soofi S was primarily trained on English and German texts and achieves top scores among open-source models in its size class for English; in German, it leads its peer group. Soofi S is initially being released as a base model that can already be fine-tuned for specific domains; followed by fine-tuned variants for dialogue and agent applications.<\/p>\n

\u201cWhoever controls the base models controls a central part of future digital value creation and increases their sovereignty and resilience. With Soofi, we are creating an open foundation on which companies, small and medium-sized enterprises, and the public sector can develop transparent AI applications based on their own data without becoming permanently dependent on individual non-European models,\u201d says J\u00f6rg Bienert, Managing Director of the Center for Sovereign AI at the German AI Association.<\/p>\n

There is a particular focus on transparency: The consortium will not only provide model weights but also publish technical documentation on training methodology, data preparation, and the data pipelines used. This will make Soofi S more verifiable for companies, government agencies, and researchers, as well as adaptable to specific application areas. Soofi S and subsequent models are trained on Telekom\u2019s Industrial AI Cloud in Munich using Nvidia\u2019s open-source AI framework. Initial results show that the Soofi S base model can keep pace with\u2014or even outperform\u2014international models of comparable size in German and English benchmarks.<\/p>\n

\u201cSoofi S is not intended as just another general-purpose chat model, but rather as a technical foundation for industrial AI. Crucially, Soofi S not only performs well in benchmarks but can also be deployed reliably, efficiently, and transparently in production,” says Nicolas Flores-Herr, technical project manager for Soofi and team lead at Fraunhofer IAIS.
 <\/p>\n

About the Project Partners<\/h3>\n

The Soofi consortium brings together research institutions, universities, and AI companies from Germany. The project is coordinated by the German AI Association.
Participants include:<\/p>\n