Installing Your Own LLMs: Hands-On Session

Take full ownership of your AI tools by running the latest open-source large language models directly on your computer. This hands-on session will guide participants through installing and configuring local LLM software, allowing them to explore AI capabilities while maintaining control over their data and workflows.

What We Will Cover

• Step-by-Step Setup: Installing and configuring Ollama across Windows and macOS environments.
• Lightweight Model Deployment: Downloading and running efficient 1B-parameter edge models (such as Google Gemma 4:e2b and/or Gemma 4: 12b) designed to run smoothly on standard laptops without requiring a high-end dedicated GPU.
• The "Airplane Mode" Test: Running prompts completely disconnected from the internet to experience true local inference and absolute data privacy.

Prerequisites: None. Participants may use an AI+ Studio laptop or bring a laptop running Windows 10/11 or macOS with at least 15 GB of free disk space. No prior coding or command-line experience is required.

Location: AI+ Studio, Weaver Science-Engineering Library, Room 212