Kolibri
A European open reasoning model for German and English. A 78B mixture-of-experts with 3.5B active per token, a 262K-token context (tested up to a million) and tool calling.
- Developer
- Aleph Alpha, Germany
- First release
- Oct 2026
- Latest release
- Oct 2026
- Sizes
- 78B-A3.5B
- License
- Commercial use allowedApache 2.0
- Russian
- Not supported
- Running
- On your own serverNeeds a GPU
- Industries
- Public sector, Legal, Documents and accounting, Software development
What it does
- answers over long documents and RAG
- an agent that calls tools
- extracting structured data from documents
- coding help
Where it is used
Hardware requirements
Versions
- Kolibri 1 BF16
- Kolibri 1 (FP8)
How to run it
I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.
Frequently asked questions
Can Kolibri be used in a commercial project?
Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.
What hardware does Kolibri need?
At minimum: Server with several GPUs — flagship versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.
Does Kolibri support Russian?
No. The developer documentation lists the supported languages and Russian is not among them.
Where can I download Kolibri and what does it cost?
The Kolibri weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.
How I deploy it for clients
- SelectionI pick the model size for your task and hardware and test it on your examples.
- DeploymentI deploy it on your server or in a closed network and provide an API.
- Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
- IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.
Similar models
OpenAI's first open models since GPT-2. Reasoning and tool calling; the smaller version fits on a single GPU.
DetailsTextMistralMistral AI · FranceCommercial use with conditionsEuropean models focused on speed. Mixtral was one of the first open mixture-of-experts models; there are versions for images (Pixtral, Medium 3.5), Lean proofs and moderation (Shieldstral).
DetailsTextQwenAlibaba · ChinaCommercial use with conditionsA family of language models with strong Russian language support, from small versions for a laptop to a flagship on par with commercial APIs.
DetailsSource: huggingface.co/Aleph-Alpha/Kolibri-1. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.


