Locally AI: Run Qwen, Gemma AI Models on iPhone

When it comes to AI, many of us use ChatGPT, Claude and even Grok. If you want to chat privately, you will need to look elsewhere though. Locally AI is just the app for the job. It lets you run Llama, Gemma, and Qwen on your iPhone and iPad. It is powered by Apple MLX and works without a login or internet connection. It is optimized for M and A chips.

This app can run Llama 3.2, Gemma 3, and Qwen 3. You will be able to use them to do what you can do with GPT, including analyzing images, asking complex questions, and generating text. You can use this app to create custom shortcuts. It supports unlimited chats.