Tutorials Intermediate
Run a Local LLM on Android with llama.cpp + Vulkan
Compile llama.cpp with Vulkan in Termux and run a quantized LLM on your Android GPU, no root.
9 min read·Kodetra Technologies
8d agoHow-to content for builders, indie hackers, and AI engineers. Less theory, more shipped code.
Tutorials Compile llama.cpp with Vulkan in Termux and run a quantized LLM on your Android GPU, no root.
Mobile Open your app from any https URL with Expo Router. iOS + Android setup that actually works.
Mobile New Compose 1.11 Grid composable: tracks, gaps, Fr units, adaptive 2D layouts.