> ## Documentation Index
> Fetch the complete documentation index at: https://docs.edge0.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Quick Start

> This page helps you choose a device and a model and complete your first local chat. For detailed installation steps, see the platform guides.

**1. Choose a device**

First check [Device Requirements](/device-requirements) to confirm the system, hardware, and available space.

| Platform | What to prepare before chatting |
| - | - |
| macOS | [Build and open the desktop app](/macos-guide) |
| Windows | [Build the engine and desktop app](/windows-guide), and set up the Python environment used for model conversion |
| iOS | [Install the app through Xcode](/ios-guide); the model must be placed in the project before building |
| Android | [Build and install the app](/android-guide), then import the converted model onto the device |

macOS and Windows download models inside the app; iOS and Android require preparing the model on a computer first.

**2. Choose a model**

For your first use, start with **Edge0 8B**: it is smaller and faster to download and load. When your device has enough resources, you can try **Edge0 35B**.

Full model names:

* `Edge0-8B-A1B-preview`
* `Edge0-35B-A3B-preview`

Your device

Requires:

Open the  guide →

For specifications, download links, and measured data, see [Models: 8B vs 35B](/models-8b-vs-35b).

**3. Prepare and load the model**

**macOS**

Open **Models**, select a model, and click **Download**. When the download finishes, click **Load model**, then go to the chat page.

**Windows**

Open **Models**, select a model, and click **Download**. After the download finishes, the app converts the model on your machine automatically. When conversion finishes, click **Enable**.

**iOS**

Before installing the app, follow the iOS guide to place the model into `Models/` and complete the build. After opening the app, select **Edge0 8B** or **Edge0 35B**.

If a model shows **Not included**, it was not bundled into the installed app. Add the model, then rebuild and reinstall the app.

**Android**

After importing the model as described in the Android guide, open **Models**, tap **Refresh**, then tap **Load** for the model you want to use.

**4. Send your first message**

Go to the chat screen and enter:

> Explain what a local language model is in three sentences.

Send it and wait for the reply. The first load and the first turn are usually slower than later ones. Once you see the model's reply, you have completed your first local chat.

Once a model is ready, responses are generated on your device without using a cloud model service. Downloading models and building the app still require a network connection; see [Privacy & Data Handling](/privacy-and-data-handling) for details.

## No reply?

First confirm that the model is loaded, not just downloaded:

* macOS: confirm you clicked **Load model**, and check on the **Service** page that the local service is running.
* Windows: confirm model conversion has finished and that you clicked **Enable**.
* iOS: confirm the selected model does not show **Not included**.
* Android: confirm the model is imported, then tap **Refresh** and **Load** in order.

For further troubleshooting, see [Troubleshooting](/troubleshooting).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.