← Sunday, October 4, 2026Models & trainingDeep dive

Kolibri combines 78B MoE parameters with German-based training infrastructure

tej.as 14 min read Editor score 7/10

Kolibri uses 78B total parameters with about 3.5B active per token, and was trained from scratch on infrastructure in Germany and Finland. The account also reports strong evaluations in German and English, useful context for teams assessing open-weight models.

What

Kolibri is an open-weight German-English mixture-of-experts model trained from scratch on infrastructure in Germany and Finland.

How

A router selects a few experts for each token; the model has 78.1 billion total parameters and uses 3.46 billion per token, with native context of 262,144 tokens.

Why it matters

Its deployment freedom and German and Finnish training infrastructure are intended to support sovereign use, including keeping organizational data on-premise.

Read on tej.as → Hacker News · 11 comments

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.