Run Powerful AI Locally: Install Ollama on Ubuntu Linux – Complete Guide

Want to run large language models like Llama, Gemma, or DeepSeek completely offline on your Ubuntu machine? Ollama makes it incredibly easy. It’s a lightweight, open-source tool that lets you download and run powerful AI models locally with simple terminal commands — perfect for privacy, zero API costs, and fast development.

Step-by-Step Installation on Ubuntu

1. Update Your System
   Open the terminal and run:

   sudo apt update && sudo apt upgrade -y
   

2. Install Ollama
   Use the official one-line installer:

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

   This automatically sets up Ollama and starts the service.

3. Verify Installation
   Check the version:

   ollama --version
   

4. Download & Run Your First Model
   Pull a model (start with smaller ones like llama3.2 or phi3 for testing):

   ollama pull llama3.2
   ollama run llama3.2
   

   Now you can chat directly in the terminal!