Aleph Alpha 发布 78B 参数开源模型 Kolibri，权重按 Apache 2.0 开放
Aleph Alpha releases Kolibri, an open-weight model that makes the case for European AI sovereignty
评分 58
导读
Aleph Alpha 发布德英混合专家模型 Kolibri，总参数 78B，每个 token 约激活 3B，训练数据中德语占比超过 21%。模型在德国和芬兰的 768 块 B200 GPU 上训练，权重以 Apache 2.0 许可证免费开放。
推荐理由
78B 参数每 token 仅激活约 3B，权重按 Apache 2.0 开放，可作为观察欧洲主权 AI 开源路线的具体样本。
主体与标签
Aleph AlphaKolibri#模型发布#开源生态#数据/训练#部署/工程
正文
Aleph Alpha has released Kolibri, a German-English language model with 78 billion parameters, about three billion of which are active per token through a mixture-of-experts architecture. Aleph Alpha claims Kolibri sits on the Pareto front of quality and operating cost in both languages, outperforming compared models with similar architectures, some significantly older (March, April 2026), on either metric. German accounts for 21.3 percent of the training data, backed by a dedicated German data pipeline the company built for the project. Chinese models were also used to generate synthetic training data.
Aleph Alpha says Kolibri targets public administration, aviation, and industry. The model was developed under European law with the EU AI Act in mind, supports context windows of up to one million tokens, and was trained on 768 B200 GPUs in Germany and Finland, according to the tech report . The weights are available under an Apache 2.0 license on Hugging Face .