Most engineers default to cloud AI without questioning the cost, the privacy trade-offs, or the dependency it creates — and the token bill grows with usage. How one freelancer moved an AI-assisted development workflow from 100% cloud to 90% local: the hardware, the models that actually perform, the honest downsides, and where cloud still wins.

Most engineers and businesses default to cloud AI without questioning the cost, the privacy trade-offs, or the dependency it creates. As usage grows, the token bill grows with it, and switching later feels like a bigger project than it should be.

In this session Hans shows how he moved his own AI-assisted development workflow from 100% cloud to 90% local, as a full-time freelancer relying on AI daily for real client work. This was not a weekend experiment. It meant picking the right hardware, choosing models that actually perform well locally, and rebuilding habits around tools he used to take for granted.

He walks through how he evaluated whether local AI made sense for his workload, how he set up the infrastructure — hardware, models and tooling — and how he integrated it into his daily development flow. Along the way: the real benefits, the genuine downsides, and where cloud still wins.

You leave with a practical framework for deciding whether local AI fits your needs, and a step-by-step path to make the switch yourself.