德国团队搞了个30B开源模型，英德双语都很强，还只用了德国电信的本地云算力，跑长文本也不掉速。
德国研究联盟发布开源语言模型Soofi S 30B-A3B，基于德国电信慕尼黑云基础设施训练。该模型采用高效混合架构，每次调用仅激活316亿参数中的部分，长文本下保持稳定吞吐量。训练数据刻意偏向德语，在德语和英语基准测试中均超越所有完全开源竞品。
German AI consortium releases Soofi S, an open 30B model that tops benchmarks in both English and German
A German research consortium has released Soofi S 30B-A3B, an open language model trained entirely on Deutsche Telekom's cloud infrastructure in Munich. The model uses an efficient hybrid architecture that activates only a fraction of its 31.6 billion parameters per token, keeping throughput steady even at very long contexts. With a training dataset deliberately weighted toward German, Soofi S tops all fully open competitors on both German and English benchmarks. The article German AI consortium releases Soofi S, an open 30B model that tops benchmarks in both English and German appeared first on The Decoder .