Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported
Python
Merge pull request #136 from Edge0-AI/fix/app_icon
chenbin11200c7ee73d5dfb3
Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported