Running local LLMs with Ollama

​In this 2-hour, fully hands-on coding session, we are taking AI offline. You will learn how to deploy, run, and interact with Large Language Models locally on your own hardware using Ollama. We will write Python code to spin up models like Llama 3, handle API requests without internet access, and wire up local function calling. By the end of this workshop, you’ll have a functioning, zero-cost AI backend running entirely on your machine - an absolute game-changer for building privacy-first SaaS products or iterating rapidly at your next hackathon without burning through API credits