---
title: "Aleph Alpha releases Kolibri, open-weight 78B English-German MoE model"
url: https://www.parallelquant.com/posts/aleph-alpha-releases-kolibri-open-weight-78b-english-german-moe-model-a4a817
source_name: "MarkTechPost"
source_url: https://www.marktechpost.com/2026/10/04/aleph-alpha-releases-kolibri-a-78-1b-open-weight-english-german-moe-model-with-only-3-46b-active-parameters/
published: 2026-10-04T07:01:04.000Z
topics: ["llms", "open source"]
publisher: "Parallel Quant"
---

# Aleph Alpha releases Kolibri, open-weight 78B English-German MoE model

*2026-10-04 · Source: [MarkTechPost](https://www.marktechpost.com/2026/10/04/aleph-alpha-releases-kolibri-a-78-1b-open-weight-english-german-moe-model-with-only-3-46b-active-parameters/)*

Kolibri is a 78.1B-parameter Mixture-of-Experts (MoE) model activating only 3.46B parameters per token. It has a 1M-token context, per-request reasoning effort, and Apache 2.0 FP8 weights that run on a single B200 or H200 GPU.

**Why it matters:** A very sparse design with permissive licensing puts large-model capacity within single-GPU reach for European organizations that want data-sovereign deployments. It is also the same company whose study on Chinese models' bias markets sovereign AI, so expect it to position Kolibri as a regional alternative.

**Topics:** llms, open source

---
Read the original: https://www.marktechpost.com/2026/10/04/aleph-alpha-releases-kolibri-a-78-1b-open-weight-english-german-moe-model-with-only-3-46b-active-parameters/
Canonical: https://www.parallelquant.com/posts/aleph-alpha-releases-kolibri-open-weight-78b-english-german-moe-model-a4a817
Published by Parallel Quant — https://www.parallelquant.com