Aleph Alpha Kolibri - Sovereign German LLM with 78B parameters
Show HN: Germany's new sovereign AI model Kolibri
Aleph Alpha Kolibri is a new open-weight large language model for German and English, released under the Apache 2.0 license. It uses a mixture-of-experts architecture with 78 billion parameters, activating only 3.5 billion per token. Trained from scratch on infrastructure in Germany and Finland, Kolibri excels at German language tasks, long-context understanding, and reasoning. It features a tokenizer optimized for German compound words, a 262k token context window (tested up to 1M), and four levels of reasoning effort. Ideal for sovereign AI deployments, it ensures data privacy and compliance with EU regulations.
Sovereign means full freedom of deployment and intellectual-property safety, so compliance comes as an inherited property.
- miellaby
The paper explains absolutely everything as if it was a tutorial "how to made your own modern agentic LLM". They even tell how they made their dataset. https://aleph-alpha.com/downloads/tech-report.pdf ; It's the first time I see this level of openness.
- tomComb
For a post to make such a big deal about sovereignty it is a bit misleading to not mention that the company is slated to be merged with Cohere, a Canadian company.
And that is a good thing - no need to hide it. Given the growing cost of keeping up, these few non-US, non-Chinese companies really need to do more sharing of efforts and costs.
Canada too is very much in need of sovereign AI options, but funding that on its own would be pretty much a waste of money. Would love to see this new German Canadian company cooperate with Mistral too, or maybe one of the Korean AI companies.
- niemandhier
I think at the moment the main thing a sovereign AI model needs to be good at is auditing the results of other models.
Right now one could run an open model for most government applications and it would be good enough, you just cannot trust any of these.
So having a sovereign controlled model audit the first one would basically act like a “trust adapter”.
If the second model is cheap and fast enough, there is a business model.
You don’t even need to audit all the intermediate steps, just tool calls and end results.
- spijdar
The absence of any comparison to Qwen3.8 Flash, another MoE model with a small-ish (6B) number of active parameters, is pretty striking. Instead, it's compared with Qwen3-Next 80B-A3B, a model released almost a full year ago.
I get that doesn't invalidate the real "point" of the model, but...
- 9dev
Aleph Alpha is just a sad joke by now. The talent isn't there anymore, they never managed to catch up to the other labs, failed to deliver on several projects, and by now are just a cash grab for the investors.
- Lucasoato
> 4. It thinks in German
This means that it’s always on time, it uses acronyms for everything and when there’s a decision to be made, it sets up a committee.
- driverdan
IMO the announcement is better https://aleph-alpha.com/en/blog/kolibri-has-landed-a-soverei...
- martianvoid
I just tried to play around with it on my RTX pro 6000 setup, it spends way too many tokens on overthinking stuff even if it’s able to catch the correct approach
Its speed is pretty good on the other hand with only 3B active parameters I am getting around 170 tkn/s on fp8