Skip to content
NewA calmer, faster ZeroHour

Aleph-Alpha/Kolibri-1 — new model trending #28 on Hugging Face

Hugging Face trending modelsby Aleph-Alpha ()10 min read6 · 3 reads
AI summary · grok-4.7Summaries by Vani AI

Aleph Alpha released Kolibri-1, an Apache 2.0 78B MoE reasoning model for German and English.

Aleph Alpha released Kolibri-1, an Apache 2.0 mixture-of-experts reasoning model aimed at German and English, with tool calling and an explicit reasoning mode. It has 78,103,074,560 total parameters and 3,457,573,120 active per token, using 384 experts per layer with one shared and six routed. Weights are float8 in 128 by 128 blocks; the footprint is about 78 GB. The model was pre-trained on 20 trillion tokens on 768 NVIDIA B200 GPUs for 21 days, followed by 3.44 trillion mid-training tokens and a long-context stage, for about 6.4e23 FLOPS. Native context is 262,144 tokens, with quality checked up to 1,048,576; the knowledge cutoff is 18 June 2026.

Key facts
  • 78.1B total parameters with about 3.46B active per token.
  • Apache 2.0 FP8 weights; memory footprint is about 78 GB.
  • Context validated to 1,048,576 tokens; 262,144 recommended for serving.
  • Pre-training used 20T tokens on 768 NVIDIA B200s over about 21 days.
  • Supports reasoning and tool calling in German and English.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

10 min read at huggingface.co

text-generation · 0 downloads · 140 likes · license apache-2. 0

Hugging Face trending models

By Aleph-Alpha · huggingface.co

Read the full article at Hugging Face trending models

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.