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)→
More from Models
- Gemini beats GPT-6 Astra at robot capture the flag, winning 70% of matches — chris_j_paxton · 2026-09-22
- 105 Planted Bugs Put Grok 4.7 at 28.7 vs GPT-6 Astra's 45 in Real-Repo Coding Test — PawelHuryn · 2026-09-22
- Regression on OpenAI's GPT-5.6 Benchmark Data Backs Out Their λ Values — tobyordoxford · 2026-09-22
- Developer Burns 1.46B Tokens in 13 Hours, Jokes He's "Part of the Infrastructure" — MaziyarPanahi · 2026-09-22
- Swarm scaling needs squared inference to match chain-of-thought gains, analysis of OpenAI curves finds — tobyordoxford · 2026-09-22
- User claims Gemini 4 Pro in production isn't the model on benchmarks — Ambroverse · 2026-09-22