Aleph Alpha releases open model Kolibri
What happened
On 5 October 2026, German company Aleph Alpha released the open-weight model Kolibri, positioning it around European AI sovereignty. According to The Decoder, Kolibri is a 78B-parameter German-English bilingual model using a mixture-of-experts architecture that activates about 3B parameters per token. The company says the model sits on the Pareto frontier for quality and running cost in German and English, scores 71% on German benchmarks and decodes faster than comparable models such as GPT OSS A5B, Qwen 3.6 A3B and Gemma 4 A4B. Coverage so far covers only the release and performance claims, with no further developments.
Written by AI from the reports · updated 11 d ago
Timeline
Follow the reports to see the event from each side.
- The DecoderAleph Alpha releases Kolibri, an open-weight model that makes the case for European AI sovereignty
Aleph Alpha has released Kolibri, a German-English mixture-of-experts model with 78 billion parameters, about three billion of which are active per token. Over 21 percent of the training data is German. The model was trained on 768 B200 GPUs in Germany and Finland, and the weights are freely available under the Apache 2.0 license.