The Local LLM Index / On-Device & Mobile / #30
leonickson1/Swiftlet
by leonickson1 · On-Device & Mobile · updated 1d ago
Swiftlet is a Swift and Metal runtime that runs large Qwen Mixture-of-Experts models locally on Apple devices by streaming expert weights from storage, enabling 35B and 80B models to run with low RAM, including on iPhone.
72
momentum
634
stars
34
forks
#30
rank
local-llmmixture-of-expertson-device-aiqwenswift
View on GitHub →