RELEASE · MODELS · #1537
Aleph Alpha releases Kolibri, a 78B German–English MoE model with 1M-token context and open weights
Aleph Alpha has released Kolibri, a 78-billion-parameter German–English mixture-of-experts model that activates about 3 billion parameters per token, supports context windows up to one million tokens, and was trained on 768 B200 GPUs in Germany and Finland. The company says German makes up 21.3% of the training data, that Chinese models were used to generate synthetic data, and that Kolibri sits on the Pareto front of quality and operating cost; the weights are published under an Apache 2.0 license on Hugging Face and the model is positioned for public administration, aviation, and industry with EU AI Act compliance in mind.
KEY POINTS
- Aleph Alpha has released Kolibri, a 78-billion-parameter German–English mixture-of-experts model that activates about 3 billion parameters per token, supports context windows up to one million tokens, and was trained on 768 B200 GPUs in Germany and Finland.
- The company says German makes up 21.3% of the training data, that Chinese models were used to generate synthetic data, and that Kolibri sits on the Pareto front of quality and operating cost; the weights are published under an Apache 2.0 license on Hugging Face and the model is positioned for public administration, aviation, and industry with EU AI Act compliance in mind.
- An open‑weight, EU‑developed MoE model with large context and German‑centric training data strengthens European AI sovereignty and makes deployable, compliant models more accessible.
WHY IT MATTERS
An open‑weight, EU‑developed MoE model with large context and German‑centric training data strengthens European AI sovereignty and makes deployable, compliant models more accessible.