OpenWeightsTerminal
Models

AliceAI-Foundation-80B-A3B

Yandex · MoE 80B-A3B

Params

80B / 3B act

Fastest decode

65 tok/s

M5 Max 128GB · Q4_K_M GGUF · llama.cpp

Refusal

Official

Setups

1

Best reported pair · not live serving speed ↗

Run this model

Runs on

Quoted one-stream decode on real boxes.

View all

Get it running

  • 1. DownloadPuts the weights on this computer.
    huggingface-cli download Yamada114514/AliceAI-Foundation-80B-A3B-Base-GGUF
  • 2. Start itUse this only if the download is GGUF.
    llama-server -hf Yamada114514/AliceAI-Foundation-80B-A3B-Base-GGUF
  • Open the weightsHugging Face ↗