Skip to main content
← Back to news

Aleph Alpha releases Kolibri: 78B parameters, 1M context, built in Europe

Model releases
Source:Aleph Alpha
Aleph Alpha's new sovereign Open-weight model, trained from scratch in Germany: 78B parameters (3.46B active) with up to 1M tokens of context. Built for mission-critical environments - multi-step reasoning, structured extraction, RAG and reliable tool calling, with native German and English. Weights are on Hugging Face, with a full technical report.
Read original article

Related articles

Aleph Alpha's Kolibri: the 78B MoE that runs (almost) locally

Kolibri ships 78B open-weight parameters in an FP8 format built for local hardware: 3.46B active per token, Apache 2.0, context up to 1M. We test it: real VRAM costs and current limits.

gpt-oss: OpenAI's open reasoning model

21B total parameters but only 3.6B active, native MXFP4 weights and 128K of context: OpenAI's first open reasoning model fits in 16GB. What that means in practice.

Ling 3.1 Flash: 560B open-weight with MIT license and 1M context — what changes if you have 24GB of VRAM

Ling 3.1 Flash ships 560B open-weight parameters under an MIT license with 1M context. It won't fit in 24GB of VRAM, but the quantizations, 25B active MoE and the real numbers change the calculation.

Get the next local-AI briefing

Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.

After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.

Related resources

Tools and resources from the iaLocale archive relevant to this content.

🧪

Hugging Face Diffusers

Frameworks

Hugging Face's Python library for running the pipelines of generative models: image, video, and audio. The standard way to run models like Qwen-Image locally, with CUDA support and CPU offload for lower-memory GPUs.

🤗

Hugging Face Transformers

Frameworks

The standard library for NLP and multimodal models, with thousands of pre-trained models.

🦋

Kolibri 1 (78B)

Models

Aleph Alpha's MoE: 78.1B parameters (3.46B active per token), Apache 2.0, FP8 weights, context up to 1M tokens, reasoning mode and tool calling. Built for mission-critical workloads on local hardware.

🌐

Open WebUI

Software

Full ChatGPT-style web interface for Ollama and llama.cpp: multi-user accounts, organized conversations, document management for RAG, per-model system prompts, tools and plugins. Version 0.11.4 (September 2026) makes file metadata travel with the retrieved chunks and runs hybrid search natively in the database: large knowledge bases are much faster. The simplest way to turn your local AI into an everyday product.

Browse all resources