You can run your own AI on your computer. Most people set it up wrong and get a slow, forgetful chatbot. At GTC 2026 an NVIDIA product manager and an Ollama engineer spent 33 mins on doing it right. 07:38 - quantization and why Q4_K_M is the default 11:04 - picking a model: VRAM, benchmarks, your own tests 19:08 - Claude Code on a local model with Ollama Launch 24:20 - the context limit when running agents locally 28:17 - structured outputs for pulling data out of documents I've seen $500 courses that teach less than this. Watch it first, then read the guide below. It takes you from zero to a working AI on your computer in 10 steps.