Install Ollama

Ollama runs models on your PC and exposes an OpenAI-compatible HTTP API (default port 11434).

Windows

1. Open https://ollama.com/download and download the Windows installer.
2. Install and start Ollama (tray icon should appear).
3. Open Command Prompt or PowerShell:

ollama --version

A version number means install succeeded.

macOS

1. Download the macOS build from https://ollama.com/download and drag it into Applications.
2. On first launch, allow network permission.
3. Open Terminal:

ollama --version

Verify the local API

With the service running, open in the PC browser:

http://127.0.0.1:11434

Or in a terminal:

curl http://127.0.0.1:11434/api/tags

JSON (model list, possibly empty) means the API is listening.

Next

• Download and pick models
• Enable LAN access (required for phone → PC)