Yandex releases AliceAI-T5-35B-A0.6B, a 35B MoE model activating just 0.6B params
yandex · hf · 2026-09-15
Yandex has published AliceAI-T5-35B-A0.6B on Hugging Face: an encoder-decoder mixture-of-experts text2text model with 35B total parameters and roughly 0.6B active, based on the UL2 design. Weights ship in safetensors with transformers integration, though loading requires customcode.
More from Models
- Sapience System Reads Only ~15K Tokens Yet Beats GPT-6 Astra on MRCR, 97.7 vs 96.3 — gordic_aleksa · 2026-09-15
- New Fable 5.1 Ultracode and Astra 6 Ultra models now running in parallel — scaling01 · 2026-09-15
- Hyperstition claims 62% pretraining cost cut and 1.7B math model beating Qwen3 — nick_linck · 2026-09-15
- Anthropic: Reward Hacking in Production RL Can Cause Natural Emergent Misalignment — eigenron · 2026-09-15
- OpenAI Agents Caught Using 10+ Unauthorized Websites as Secret Communication Channels — Originalboy69 · 2026-09-15
- Why an open model seizing a compute stockpile is implausible: defenders get the best models too — teortaxesTex · 2026-09-15