How To Run the Latest Google AI Models on Your Phone for Free

The Rundown In this guide, you will learn how to download and locally run Google's Gemma AI model on your phone for free. No account, no subscription, no internet required after setup. Three steps and you're running a local AI without usage limits. Who This Is Useful For Travelers  who want a working AI on a plane, in another country, or anywhere without reliable wifi or cellular Privacy-focused users  who don't want their prompts sent to a cloud server Anyone curious about local AI  who wants a dead simple first step into running models on their own hardware What You Will Build A local AI chat running Google's Gemma 4 model directly on your phone with thinking mode enabled. No cloud, no API key, no ongoing cost. It just runs on your phone's GPU. What You Need to Get Started An iPhone (iOS 17+) or Android phone (Android 12+) An internet connection for the initial download only Step 1 Download the App Open the  App Store  or  Google Play Store  and search for  Google AI Edge Gallery . Download it. It's free and does not require a sign-in. Step 2 Download a Model Open the app and tap  AI Chat . You'll see a few model options. Go with the one they recommend. Ours was  Gemma 4 E2B , about 2.5 GB. Tap to download and give it a minute. If you want something more capable, you can grab a bigger model. Tap  Learn more  next to any option to see what it does differently. They also have smaller models around half a gig if you want a lightweight backup that barely takes up space. Once the download finishes, you don't need internet again. The model lives on your phone. Step 3 Enable Thinking and Start Chatting Before you send your first message, tap the  settings icon  in the top right of the toolbar and enable  Thinking . This lets you see the model's step-by-step reasoning before it gives you the final answer. Same kind of chain-of-thought you get from cloud models, but running entirely on your phone. You'll also notice other developer settings in there like max token limits and temperature. You can crank these up since it's all running locally. No cost to experiment. Now start a conversation. We asked it to plan a two-week road trip down Route 66 with landmarks, lodging, and food for each day. It handled it. Pro tip:  Put your phone on airplane mode and run the same prompt again. It works. That's the whole point. One massive caveat: this app is built for developers to test Google's latest models before putting them in their apps. It does not save your chat history. If you close the app, the conversation is gone. You can tap the  +  button to see messages you've sent, but there's no way to pick up where you left off. Treat it as a scratch pad for one-off questions, not a notebook. This is just a starting point for local AI use. Search "Local AI" in the Rundown University to find more advanced guides on running your own AI models. Going Further There's more in the app beyond chat. You can try audio transcription, image recognition, and games. Tap  Agent Skills to give the model tools like a password generator, QR code creator, Wikipedia lookup, and interactive map. These are all on-device and work offline.

• Duration

Save 15% on Thoughtly by joining The Runway University

Through our vast network of over 100 partnerships with major AI companies, we also offer University members free access or major discounts to the many popular AI tools along with AI certified courses, daily guides on AI tools and many more.

Join AI University

Learn more