Decoding Local AI - A Plain-English Guide to Running LLMs on Your Own GPU

​Curious about running AI directly on your own hardware? This beginner-friendly talk breaks down the basics of Local LLMs. We’ll decode the messy alphabet soup of AI model names, explain how graphics cards (GPUs) power these models, and demystify concepts like Quantization, QAT, and MTP without complex math. You'll leave with a clear understanding of how local AI works and what your current setup can actually run!

​Presenter: Matthew Tiner, Infrastructure and Cloud Specialist