15:54
2026-09-10
github.com
large-language-models
A 35B language model running on an iPhone using only 1–2.5 GB of peak memory
Edge0-AI released edge0, an open-source streaming MoE inference framework that runs a 35B-parameter language model on Apple Silicon iPhones at roughly 2.9 GB peak active memory for the edge0-35b tier …