This guide demonstrates how to set up and run Large Language Models (LLMs) with Ollama inside Daytona workspace, significantly improving productivity. To follow this guide, you'll need to have a Python environment and chat interface set up. The process involves creating a dev container using a devcontainer.json configuration file, writing project files like ollama_chat.py and requirements-dev.txt, and then running LLMs through Daytona's containerized setup. The devcontainer.json file specifies the development environment settings, including the image, features, customizations, and post-start command. The guide also covers adding a chat script, creating a requirements-dev.txt file, initializing Git, committing changes, and pushing to a remote repository. Finally, it explains how to run LLMs with Ollama in Daytona, using GitHub as a provider, and opens a workspace in VS Code.