Installing Ollama

This guide walks you through downloading, installing, and verifying Ollama on your local machine so you can run large language models (LLMs) like LLaMA 3.2 straight from your terminal.

1. Downloading Ollama

Visit the Ollama website and choose your operating system. Below is a quick reference for each platform:

Select the download button for your OS, then you’ll land on a page like this:

2. Installing on macOS

Once the .zip file has finished downloading:

1. Open Finder and navigate to your Downloads folder.
2. Unzip the archive and double-click Ollama.app.
3. When prompted, click Open.
4. macOS will ask to move the app to Applications—confirm to complete the install.

3. Verifying the CLI

Launch your terminal. On first run, you may be asked to install the Ollama CLI—type yes to proceed. Once installed, confirm everything is set up by running:

ollama

You should see output similar to:

Usage:
  ollama [flags]
  ollama [command]

Available Commands:
  serve   Start ollama
  create  Create a model from a Modelfile
  show    Show information for a model
  run     Run a model
  stop    Stop a running model
  pull    Pull a model from a registry
  push    Push a model to a registry
  list    List models
  ps      List running models
  cp      Copy a model
  rm      Remove a model
  help    Help about any command

Flags:
  -h, --help      help for ollama
  -v, --version   Show version information

Use "ollama [command] --help" for more information about a command.

Congratulations! You now have Ollama installed and can run LLMs locally.

4. Next Steps

To get started, try running Meta’s LLama 3.2 model:

ollama run llama3

Explore the full set of commands with ollama help or check out the official documentation to learn how to create and manage your own models.

Links and References

• Ollama website
• Ollama Documentation