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

Aleph Alpha has released Kolibri, a 78.1B-parameter English-German Mixture-of-Experts model that activates only 3.46B parameters per token. It has a 1M-token context and per-request reasoning effort, and its Apache 2.0 FP8 weights run on a single B200 or H200. The post Aleph Alpha Releases Kolibri: A 78.1B Open-Weight English-German MoE Model With Only 3.46B Active Parameters appeared first on MarkTechPost .
This is a short summary published by AI Global Wire. The full article is owned and hosted by MarkTechPost — open it there to read it in full.
Read the full story at MarkTechPost- Verktyg
Related AI news
- Trump launches Super Intelligence Force with Jay Clayton as AI czarSiliconANGLE · October 4, 2026
- Dario Amodei’s American AI imperialismSCMP Tech · October 4, 2026
- GPT-6 Astra vs GPT-6.1 Sol vs Gemini 4 Argon vs Claude Fable 5.1: Which Frontier Model Fits Which JobMarkTechPost · October 4, 2026
- Trump launches "Super Intelligence Force" that has nothing to do with actual superintelligenceThe Decoder · October 4, 2026
- What to expect at SailPoint’s Navigate event: Join theCUBE Oct. 6–7SiliconANGLE · October 4, 2026
- India needs its own AI safety framework, not a copy of US pact: Industry expertsEconomic Times Tech · October 4, 2026