Aleph Alpha Releases Kolibri: A 78.1B Open-Weight English-German MoE Model With Only 3.46B Active Parameters
Aleph Alpha has released Kolibri, an open-weight Mixture-of-Experts (MoE) language model built for German and English. Kolibri has 78.1B total parameters but activates only 3.46B, or 4.4%, per token. It accepts up to 1,048,576 tokens of context, lets users set reasoning effort per request, and ships under the Apache 2.0 license on Hugging Face. The target is sovereign deployment in regulated sectors such as public administration, industry and aerospace. Is it deployable? Yes. The FP8 checkpo
Get smart on it
Kolibri is an open-weight language model designed for English and German that contains 78.1 billion total parameters but only activates 3.46 billion per token, making it efficient to run on a single high-end GPU. The model uses a Mixture-of-Experts architecture where each token is routed to 6 out of 384 specialized experts plus one shared expert, and combines sliding-window attention with full attention layers to support up to one million tokens of context. It was developed entirely by teams in Germany using infrastructure in Germany and Finland, with training data that included over 20 percent German content, and is designed to meet European AI regulations including the EU AI Act and GDPR. The model is released under the Apache 2.0 license and benchmarks show it achieves the highest overall scores in English and German among comparable models while using fewer active parameters than denser alternatives.
Related news
Google Research Moves Federated Learning Into TEEs: Gboard Now Trains With Externally Verifiable Differential Privacy
Google Research has announced a next-generation Federated Learning (FL) system built on Trusted Execution Environments (TEEs). The research team claims externally verifiable central differential privacy (DP) guarantees for FL for the first time. What Problem Does TEE-Based Federated Learning Solve? Google introduced Federated Learning FL in 2017. It powers next-word prediction and Smart Compose on Gboard, reply suggestions in Google Messages, and Smart Text Selection in Android. Earli
Decision AI Models Explained: TypeSafe Jev vs Fastino GLiDE, GLiNER2.5-Decide and Open-Source Competitors
What are Decision AI Models? Decision AI models are a new class of model that returns a decision, not a paragraph. You send text with typed questions. The model returns choices, scores or yes/no probabilities your code can branch on directly. The category went mainstream when TypeSafe AI launched Jev after 2 years in stealth. TypeSafe calls it a ‘System One model,’ after Daniel Kahneman’s fast, intuitive System 1 thinking. Within 3 weeks, Fastino Labs shipped 2 rival
