Back to directory

DeepSeek R1 Installation Guide for Android

A step-by-step guide, with an automated installer script, for running the DeepSeek R1 model offline on a rooted Android phone using Termux, Arch Linux and Ollama.

DeepSeek R1 Installation Guide for Android

This guide walks through installing and running DeepSeek R1 locally on an Android device with no internet connection required after setup, using Termux to install Arch Linux, then Ollama inside that Arch environment to download and run the model. A companion shell script automates the whole process on a rooted phone: it updates Termux, installs the required tools, sets up Arch Linux, installs and starts Ollama, and launches the model, so a user only needs to install Git and a helper package for elevated access before running the script.

After installation, using the model again means logging back into the Arch Linux environment inside Termux, starting the Ollama server, and running the model by name. The guide recommends the 1.5-billion-parameter version of DeepSeek R1 as the practical choice for a phone, since larger versions need more RAM and a stronger processor than most devices have, and notes that performance depends heavily on the phone's own hardware.

More in Inference

See all 770
  • OpenDecision

    deepanwadhwa.github.io

    An open-source Python package that answers typed questions about application state or documents using a local natural-language-inference model, returning structured choice, score, yes/no or evidence-relation values instead of free text.

  • Lifeboat

    iterate.ai

    A local inference server that puts an OpenAI- and Anthropic-compatible API in front of open-weight language models running on hardware you control, from a laptop to a GPU cluster.

  • Claude S40

    github.com

    An unofficial Claude chat client for 2007-era Nokia Series 40 phones, built as a Java ME app plus a small Go relay server, with web search, reading mode and saved chats.