I quit ChatGPT for a free, private, and local AI called Ollama - here's why

Learn how to install and use Ollama, a free, private, and local AI tool that runs on your computer without requiring internet connection or sending data to remote servers.

Introduction

In this tutorial, you'll learn how to install and use Ollama, a free, private, and local AI tool that runs on your own computer. Unlike ChatGPT, which requires an internet connection and sends your data to remote servers, Ollama keeps everything local on your device. This means better privacy, faster responses, and no monthly subscription fees. We'll walk through the complete setup process so you can start using this powerful AI tool right away.

Prerequisites

Before starting this tutorial, you'll need:

A computer running Windows, macOS, or Linux
At least 4GB of RAM (8GB recommended)
At least 5GB of free disk space
Internet connection for downloading the software

Step-by-Step Instructions

Step 1: Download Ollama

Visit the Official Website

First, open your web browser and go to https://ollama.com/. This is the official website where you can download the software for your operating system.

Download the Appropriate Version

On the homepage, you'll see download buttons for different operating systems:

Windows users should click the "Windows" button
Mac users should click the "macOS" button
Linux users should click the "Linux" button

Choose the version that matches your computer's operating system and download the installer file.

Step 2: Install Ollama

Windows Installation

After downloading the installer, locate the file in your Downloads folder and double-click it. The installation wizard will guide you through the process. Simply click "Next" and "Install" to proceed with the default settings.

Mac Installation

On macOS, after downloading, you'll need to open the .dmg file. Drag the Ollama icon to your Applications folder. You might need to right-click and select "Open" if you get a security warning.

Linux Installation

For Linux users, open a terminal and run the following command:

curl -fsSL https://ollama.com/install.sh | sh

This command downloads and installs Ollama automatically on your system.

Step 3: Start Ollama

Launch the Application

After installation, find and launch Ollama on your computer:

Windows: Look for "Ollama" in your Start Menu
Mac: Find it in your Applications folder
Linux: Type "ollama" in your terminal

When you first run it, Ollama will start a background service that allows you to interact with AI models.

Step 4: Download Your First AI Model

Understanding Models

Ollama works with different AI models that each have specific capabilities. Think of these like different tools - one might be better for writing, another for coding, and another for answering questions. For beginners, we'll start with a general-purpose model called "llama3" which is powerful and versatile.

Download the Model

Open a terminal (Windows users can use Command Prompt or PowerShell, Mac/Linux users can use Terminal). Type the following command and press Enter:

ollama run llama3

This command tells Ollama to download and start the llama3 model. The first time you run this, it might take a few minutes to download the model files.

Step 5: Start Chatting with Your Local AI

Interactive Session

After the model downloads, you'll see a prompt that looks like this:

>>> What can you help me with?

This is where you can ask questions or give instructions. Try typing something like:

Explain what a computer is in simple terms

Press Enter and wait for the response. You'll see the AI's answer appear in your terminal.

Try Different Commands

You can ask all sorts of questions:

"Write a short poem about technology"
"How do I make a sandwich?"
"What is the capital of France?"

Each time you're done chatting, type "exit" and press Enter to close the session.

Step 6: Explore More Features

Running Different Models

Try running other models to see how they differ:

ollama run phi3

This model is smaller and faster, good for quick questions. You can also try:

ollama run mistral

This model is great for coding tasks and complex reasoning.

Creating Your Own AI Commands

For more advanced users, you can create custom prompts and save them. But for now, just experiment with asking different types of questions to see how each model responds differently.

Summary

Congratulations! You've successfully installed and used Ollama, a local AI tool that runs entirely on your computer. Unlike ChatGPT, this setup keeps your conversations private and doesn't require an internet connection after the initial download. You've learned how to download the software, install it on your system, download AI models, and start having conversations with your local AI assistant. This approach gives you complete control over your data while providing powerful AI capabilities right at your fingertips.

Remember, your local AI will remember previous conversations during a session, but your data stays on your computer. This means better privacy and faster responses since no data needs to travel to remote servers.