Show HN: IttyBittyAI – Qwen2.5:0.5B running on a 2017 Asus smartphone

Category: ai-ml

Tags: llm, edge-ai, postmarketos, llama-cpp, smartphone, local-inference

Score: 5.7/10 (Innovation: 6, Technical: 7, Documentation: 4, Utility: 4)

IttyBittyAI turns a 2017 Asus smartphone running postmarketOS into a local AI chatbot server using llama.cpp and Qwen2.5-0.5B. It demonstrates impressive portability and resource efficiency, achieving ~4.5 tokens/sec on an old ARM device, making local AI accessible on low-end hardware.

Target audience: AI enthusiasts, embedded developers, tinkerers

View on Hacker News