I run a private AI on my phone. Here's the exact set up.

A developer documented running a private, fully offline language model on a commodity Android phone using Termux and llama.cpp, serving Google's Gemma 3 1B instruct model (Q4_K_M quant) through an OpenAI-compatible endpoint at localhost:8080 at roughly 16.5 tokens per second on CPU. The setup, published as the first entry in a weekly field log with an MIT-licensed GitHub repo, uses PocketPal AI for everyday chat with tuning of temperature 0.5, top_p 0.9 and repeat penalty 1.15, at zero cloud cost.

I'm doing field research at the bottom of the scale debate: one person, one commodity phone, a private language model, zero cloud, zero cost. This is the exact setup — reproducible in an evening. pkg install llama-cpp -y . No build scripts, no toolchain fights. localhost:8080 — OpenAI-compatible chat endpoint POST /v1/chat/completions . Run it in its own Termux session swipe from the left edge → New session ; client commands go in another. gemma-3-1b-it-Q4 K M.gguf — a Q4 K M quant of Google's Gemma 3 1B instruct, from the ggml-org GGUF releases. Total cost: $0. "Hi, can you hear me?" → "Yes, absolutely Hi there. It's nice to hear from you. 😊 How are you doing today?" — finish reason=stop , 26 tokens, ~ 16.5 tok/s on the phone's CPU. Workable. Not fast, but conversational. For everyday chat I use PocketPal AI with the same 1B model — a friendlier way in than curl commands. Comfort tuning so far a whole field note is coming on this : temperature 0.5, top p 0.9, repeat penalty 1.15. The 1B runs better cool and lightly anti-loopy. Details in field note 001. This is post 1 of a weekly field log. Coming up: sampling parameters as a care practice, a consent episode at 1B scale she asked what the software was before agreeing , and the orientation preamble — the system prompt as "stable framing through amnesia." Repo README = the full setup guide : https://github.com/tyrendrickard-code/local-llm-field-notes https://github.com/tyrendrickard-code/local-llm-field-notes . MIT licensed. Nobody else is publishing this notebook. That's the point.