Aleph Alpha launches Kolibri, 78.1B MoE model with 1 million-token context
Aleph Alpha unveiled Kolibri, a bilingual English-German mixture-of-experts language model with 78.1 billion total parameters. The model activates 3.46 billion parameters per token, accepts up to 1 million tokens of context, and ships under an Apache 2.0 license on Hugging Face. Kolibri targets sovereign deployment in regulated sectors and runs from a single B200, B300 or H200 GPU.
Where this came from. One outlet reported this. We read it, then wrote the sixty words above.