How To Replace Siri With a Free Local Model

Open the App Store and download Locally AI.

Once it installs, open the app and continue through the welcome screen.

When the app asks you to choose a model, start with the latest Gemma model available in the app.

Gemma is Google’s open-source model family and is a strong first pick for this setup. It is good enough for normal assistant tasks and gives you a clean baseline before you start testing bigger models.

Pro tip: Download models on Wi‑Fi before you need the assistant offline. Most models are several gigabytes.

Pro tip: Model names usually include sizes like 4B, 6B, or 8B. That number is roughly the model’s parameter count. Bigger usually means more capable, but it also means a bigger download and slower performance on your phone.

Tap download and keep the app open while it finishes. This may take a few minutes because you are downloading the actual model file onto your phone, which can be a few gigabytes.

Once the model is installed, try one quick prompt before you connect it to the Action Button.

Give me a quick plan for the three most important things I should do before a 30-minute client call.

This test gives you a feel for speed and answer quality. If it responds well enough for quick assistant tasks, you are ready to bind it to your phone.

Swipe down on your home screen and search for Action Button.

Open the Action Button settings. Swipe through the options until you see Shortcut.

Tap whatever is currently set as the shortcut, then search for Locally AI.

Select Voice Mode. Your Action Button should now be set to Locally AI Voice Mode.

Press the Action Button and wait for the chime. The first time you open Voice Mode, Locally AI may ask you to download a speech-to-text model. Download it. This separate model lets the app handle voice input locally.

Pro tip: If Voice Mode does not launch right away, go back into the Action Button settings and confirm the selected shortcut says Locally AI Voice Mode, not New Chat.

Press the Action Button and ask a question out loud.

Explain the difference between local AI and cloud AI in simple terms.

Translate "I will send the document this afternoon" into Spanish.

Give me three ways to prepare for a quick client call.

Local models can be useful, but they are not perfect. They may be less reliable than large cloud models like ChatGPT or Claude. For everyday assistant tasks, the tradeoff can still be worth it: explaining concepts, translation, quick planning, and simple rewrites are all good fits.

Pro tip: After the model and speech-to-text model are downloaded, turn on airplane mode and ask another question. If it still responds, you have proved the important part: the assistant is running locally on your phone.