Yandex open-sources 80B MoE Alice model: 3B active params, 256K context

teortaxesTex · x · 2026-09-22

Yandex has released the weights of its Alice AI Foundation 80B-A3B Base: 80B total parameters with only 3B active per token, 256K context, Apache 2.0 license, available on Hugging Face.

Commenter teortaxesTex notes this is a modern small MoE (Muon, Kimi Delta-style, AttnRes, Qwen3 Next-shaped, 18T tokens) from a country that can't legally buy compute and lost most of its AI researchers in five years — estimating Yandex is 1.5 years behind as an AGI lab, roughly at Mistral's level.

Related event: Yandex Open-Sources 80B MoE Base Model AliceAI(2 posts)→

Original post →

More from Models

Models channel →