NNishchay Kaushik·Feb 13How to Run LLM Models on Old Android Devices LocallyLearn how to run local LLMs on Android in 2026. Use Termux and llama-server to run Gemma 4 & Turn your old phone into a private AI powerhouse.5 min read·nkaushik.in
PPranjali Sachan·Mar 23, 2025Deploying Gemma 1B GGUF model with llama.cpp on UbuntuThis is a step-by-step guide on deploying and interacting with quantized gemma 1b from Google using llama-server5 min read·pranjalisachan.hashnode.dev
