TLDRocket
Sign in

Mixture-of-Experts

81 summarised stories about Mixture-of-Experts, each linking back to the original source. Browse all topics →

+ Follow this topic

Key players

NVIDIA Hugging Face MarkTechPost Inkling Kimi K3 OpenAI

Sunday, 4 October 2026

Aleph Alpha Releases Kolibri: A 78.1B Open-Weight English-German MoE Model With Only 3.46B Active Parameters

MarkTechPost 1 week ago 19 ● 2 sources

Aleph Alpha released Kolibri, an open-weight English-German Mixture-of-Experts language model designed for regulated, sovereign deployments. Kolibri has 78.1B total parameters but activates 3.46B (4.4%) per token and supports up to 1,048,576 tokens of context. The release adds Apache 2.0 model weights plus a vLLM deployment path with FP8 serving, reasoning control, and tool-call parsing, enabling users to run and fine-tune it on specified NVIDIA GPUs.

Read the full story
Large Language Models Open-Weight Models Mixture-of-Experts

The daily briefing

Every AI story that matters, in your inbox by 8am.

TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the day in two minutes. Follow companies and topics for alerts, or get the briefing in Slack. Free, no spam, unsubscribe anytime.