Yandex has released AliceAI-Foundation-80B-A3B-Base, an 80‑billion‑parameter model featuring a fully custom architecture intended to compete with Qwen 35B and DeepSeek V4 Flash. Unlike Qwen3 derivatives, it is neither a fine‑tune nor post‑trained like Qwen3.5/3.6, and it currently lacks Llama.cpp support. The model is hosted on Hugging Face at https://huggingface.co/yandex/AliceAI-Foundation-80B-A3B-Base.