# llama.cpp adds support for Aleph Alpha’s Kolibri-1

> Release b11709 adds support for a 78-billion-parameter German-English reasoning model. The update does not say where users can obtain its weights.

Oossa · 2026-10-17 · https://oossa.com/en/llama-cpp-adds-support-for-aleph-alpha-s-kolibri-1

The llama.cpp project added support for Kolibri-1, a German- and English-language reasoning model from Aleph Alpha, in release b11709. The model has 78 billion parameters, with 3.46 billion active for each token, and uses a mixture-of-experts design.

The update describes support for converting and running Kolibri-1’s model architecture, including its sliding-window attention and FP8 checkpoint format. It does not provide download details or say which devices can run the model.

## The facts

- Kolibri-1 has 78 billion parameters and 3.46 billion active per token.
- llama.cpp release b11709 is published October 17, 2026.

## Why it matters

People using llama.cpp may be able to work with Kolibri-1 through the project, but the release notes do not establish where to get its weights or what hardware is needed.

## Sources & references

1. [ggml-org/llama.cpp b11709](https://github.com/ggml-org/llama.cpp/releases/tag/b11709) – llama.cpp, 2026-10-17

Last updated: 2026-10-17