Current outcome
Aleph Alpha released and open-sourced Kolibri, a German-English MoE LLM. It has 78.1B total parameters and ~3.46B active per token, with weights on Hugging Face under Apache 2.0. It supports tool calling and adjustable reasoning, with context extendable to ~1M tokens (trained to 262K). The official technical report details dataset and training recipe.
Progress timeline
2 material updates- #01
Kolibri is an open-weight LLM from Aleph Alpha for German and English
Aleph Alpha released Kolibri, an open-weight LLM optimized for German and English, accompanied by a detailed technical report that documents its dataset and training recipe.
Source evidence: tejaskumar__
- #02
欧洲开源模型Kolibri来了：3.46B激活参数，支持1M上下文
New details: Kolibri uses MoE architecture with 78.1B total and 3.46B active parameters per token; weights on Hugging Face under Apache 2.0; supports tool calling and adjustable reasoning; context extendable to ~1M tokens (trained to 262K); official benchmarks AIME 2025 96.9%, LiveCodeBench v6 85.9%.
State after update: Aleph Alpha released and open-sourced Kolibri, a German-English MoE LLM. It has 78.1B total parameters and ~3.46B active per token, with weights on Hugging Face under Apache 2.0. It supports tool calling and adjustable reasoning, with context extendable to ~1M tokens (trained to 262K). The official technical report details dataset and training recipe.
Source evidence: theblockbeats