# Kolibri: A Sovereign European Model on the Pareto Frontier

DevFeed: [Kolibri: A Sovereign European Model on the Pareto Frontier](<https://devfeed.tech/articles/kolibri-a-sovereign-european-model-on-the-pareto-frontier-99535.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.31945>)

Author: Aleph Alpha, :, Moritz Althaus, Artur Baranowski, Michael Barlow, Fabien C. Y. Benureau, Felix Berkenkamp, Amrita Bhattacherjee, Lukas Bl\\"ubaum, Duncan Blythe, Augustijn de Boer, Bastian Boll, Thomas

Published: 2026-10-26T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Sovereign AI](<https://devfeed.tech/topics/sovereign-ai.md>), [post-training](<https://devfeed.tech/topics/post-training.md>), [Training AI Models](<https://devfeed.tech/topics/training-ai-models.md>), [Dataset development](<https://devfeed.tech/topics/dataset-development.md>), [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>), [model architecture](<https://devfeed.tech/topics/model-architecture.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [managing large-scale text data in AI](<https://devfeed.tech/topics/managing-large-scale-text-data-in-ai.md>), [versioning](<https://devfeed.tech/topics/versioning.md>)

Tags: [aerospace](<https://devfeed.tech/tags/aerospace.md>), [apache-2-0](<https://devfeed.tech/tags/apache-2-0.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [code](<https://devfeed.tech/tags/code.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [development](<https://devfeed.tech/tags/development.md>), [english](<https://devfeed.tech/tags/english.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [experimentation](<https://devfeed.tech/tags/experimentation.md>), [experts](<https://devfeed.tech/tags/experts.md>), [extension](<https://devfeed.tech/tags/extension.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [industry](<https://devfeed.tech/tags/industry.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [kolibri](<https://devfeed.tech/tags/kolibri.md>), [mixture-of-experts](<https://devfeed.tech/tags/mixture-of-experts.md>), [model](<https://devfeed.tech/tags/model.md>)

## AI overview

Kolibri is an open-weight English-German mixture-of-experts model with 78.1B total parameters and 3.46B active per token, released under Apache 2.0. It is designed for sovereign and specialised deployment, especially German and regulated fields. Training uses 24T tokens, with German exceeding 20% of the data by bytes, including over 2T curated or synthetically generated German tokens. Post-training combines supervised fine-tuning with reinforcement learning on more than 1.2M internally curated tasks spanning reasoning, tool use, instruction following, code, and retrieval. The report says Kolibri lies on the quality-and-serving-cost Pareto frontier among the open models it evaluated in both English and German; this comparison is limited to that evaluated set.

## Source excerpt

arXiv:2610.31945v1 Announce Type: cross Abstract: This report introduces Kolibri, an English-German mixture-of-experts transformer with 78.1B total parameters and 3.46B active parameters per token, released as open weights under the Apache 2.0 licence. We built Kolibri for sovereign and specialised deployment, with a particular focus on German and on regulated domains such as public administration, industry, and aerospace. To support these settings, we control the full model-development process, including data, architecture, training infrastructure, post-training, and evaluation. We train Kolibri on 24T tokens across pre-training, mid-training, and long-context extension, with German accounting for more than 20% of the data mix by bytes. To reach this share, we complement German datasets with more than 2T German tokens that we curate from the web with our own pipeline and generate synthetically. Post-training combines supervised fine-tuning on curated German and English data with reinforcement learning on more than 1.2M internally curated tasks, which cover reasoning, tool use, instruction following, code, and retrieval. The model activates 4.4% of its parameters per token, and among the open models evaluated in this report, it lies on the Pareto frontier of quality and serving cost in English and German. Kolibri builds on Kolibri Origin, an earlier iteration that validated our full pipeline at scale. Both models come from our Model Factory, which connects data, experimentation, training, evaluation, and deployment through version-controlled workflows.