How to Run Open Source LLMs Locally and in the Cloud

A freeCodeCamp course taught by Andrew Brown covering how to run open-source LLMs like Gemma, Kimmy, and GLM both locally and in the cloud. The course uses practical 'smoke tests' such as building Flappy Bird clones to benchmark model performance, evaluates hardware and VRAM requirements for local execution, and explores coding harnesses like Claude Code and PI Coding Agent for building agentic workflows. Key takeaways include which models are most reliable for tool calling and structured code generation.