llama.cpp-mtp-turboquant/examples/llama.swiftui

llama.swiftui

Local inference of llama.cpp on an iPhone. So far I only tested with starcoder 1B model, but it can most likely handle 7B models as well.

https://github.com/bachittle/llama.cpp/assets/39804642/e290827a-4edb-4093-9642-2a5e399ec545