Guides

How to run an LLM on an Android phone

Updated November 8, 2026

Yes, you can run an LLM on an Android phone with a free app. You do not need root or Termux. Download a model of about 2 to 5 GB and it runs offline.

What you need

Set it up in opchat

  1. Install opchat from Google Play.
  2. Open Settings → Models → On this device.
  3. Choose a recommended model, or use Browse & Download Models to search Hugging Face.
  4. Download it on Wi-Fi, then start a chat.

GGUF or LiteRT?

These are two formats for the same idea, and opchat runs both.

GPU support on Android varies by chip. opchat uses the GPU for LiteRT on Adreno graphics, found in Snapdragon phones. On other chips it defaults to the CPU, which is more stable there. You can change this setting yourself.

Which model to pick

Start with Gemma 4 E2B. If it is too slow, try LFM3 or a small Qwen 3.5 variant. If you have 12 GB of RAM or more, try Gemma 4 E4B.

What to expect

Expect slower replies than cloud AI, some heat on long sessions, and more mistakes than large models make. If you want to compare options, see the best apps for running AI models on a phone.

Frequently asked questions

Can I run an LLM on Android without Termux?

Yes. Apps such as opchat, PocketPal AI and Google AI Edge Gallery download and run models with no command line.

How much RAM do I need on Android?

Treat 6 GB as a practical minimum for small models, and 8 GB or more as comfortable.

Does local AI use the phone's GPU?

Sometimes. It depends on the model format and the chip. In opchat, LiteRT models use the GPU by default on Adreno graphics and the CPU on other chips, and you can change this in the settings.

Try opchat

Free on iPhone and Android. Use your own API keys, or download a model and go offline.