Setup & Installation

Setting Up Your Local LLM Environment

This section guides you through installing and configuring Ollama with its native GUI interface. By the end, you’ll have a fully functional local LLM environment ready to use.

What is Ollama?

Ollama is an open-source tool that makes it easy to run large language models locally on your computer. As of 2025, Ollama includes:

  • Native GUI Application: User-friendly desktop interface
  • Model Library: One-click access to dozens of open-source models
  • CLI Tools: Command-line interface for advanced users
  • REST API: For integration with other applications
  • Cross-Platform: Works on macOS, Windows, and Linux

Why Ollama?

Ollama has become the de facto standard for local LLMs because it:

Simplifies Installation: One download, everything included ✓ Manages Models: Easy downloading, updating, and switching between models ✓ Optimizes Performance: Automatically configures for your hardware ✓ Provides Flexibility: GUI for beginners, CLI for experts ✓ Stays Updated: Regular updates with latest models and features

What You’ll Install

  1. Ollama Application: The main program with GUI and CLI
  2. Llama 3.2 Model: Our primary model for the workshop (2-3 GB download)
  3. (Optional) Additional Models: For experimentation

System Requirements Recap

Before proceeding, ensure your system meets these requirements:

Component Minimum Recommended
RAM 8 GB 16 GB
Storage 20 GB free 50 GB free
OS macOS 12+, Windows 11, Linux Latest versions
Internet Broadband connection For initial downloads

Setup Process Overview

The setup process has three main steps:

Estimated Time

  • Installation: 5-10 minutes
  • Model Download: 5-15 minutes (depending on internet speed)
  • Testing: 5 minutes
  • Total: 15-30 minutes
During the Workshop: We’ll walk through each step together. If you’ve already installed Ollama before the workshop, you’re ahead of the game! You can skip to First Chat to verify everything works.

Ready to Start?

Let’s begin with Installation!