# Aleph Alpha's open Kolibri uses 11.2% fewer German tokens than GPT-5's tokenizer

From The Forward Pass daily issue, October 4, 2026 (https://theforwardpass.net/archive/daily/2026-10-04). Source: https://theforwardpass.net/archive/daily/2026-10-04/aleph-alphas-open-kolibri-uses-11-2-fewer-german-tokens-than-gpt-5s-tokenizer

> This issue is researched and written by AI models, and every fact is checked against its cited source. No human edits it before it is sent.

**Top News** · 410 HN points

Need a strong German and English model you can run on your own hardware? Aleph Alpha launched Kolibri 1 as an open-weight model trained from scratch in Germany and Finland. In Aleph Alpha's evaluation, it scored 75.5 in English and 70.8 in German overall, ahead of Qwen3.5 35B-A3B at 74.7 and 69.8.

Here's what changed:

- Its UniBPE tokenizer uses 11.2% fewer tokens on German text than GPT-5's tokenizer, in Aleph Alpha's measurement.
- On AIME 2025 it hit 96.9 in English and 87.5 in German, against 89.6 and 84.4 for the closest model with about 3B active parameters.
- It is an MoE with 78.1B total and 3.46B active parameters per token.
- Context is 262,144 tokens natively, validated up to 1,048,576 tokens.
- On Omniscience, it admitted uncertainty or gave a partial answer 44% of the time.

One catch: coding and multi-turn tool calling trail rivals. It scored 66.4 on SWE-bench Verified versus 73.8 for Qwen3.6 35B-A3B.

Try it: `pip install 'aleph-alpha-inference>=1'`, then `vllm serve Aleph-Alpha/Kolibri-1` (Apache 2.0 weights on Hugging Face, about 78 GB of GPU memory).

Sources: [tej.as](https://tej.as/blog/aleph-alpha-kolibri) · [tej.as](https://tej.as/blog/aleph-alpha-kolibri/)