Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Gaming PC to OpenAI Server
Transforming gaming PCs into an OpenAI-compatible GPU server network for decentralized, accessible AI compute sharing and inference.
I’ll be presenting a desktop platform that turns any gaming PC into an OpenAI-compatible GPU server. The goal is to make compute accessible, collaborative, and decentralized — allowing anyone to share their unused GPU power with friends, communities, or the public.
The demo will walk through how the platform transforms a local GPU into an API-compatible endpoint, showing how it integrates with the OpenAI API format for seamless use with existing AI clients. I’ll cover the technical architecture, including GPU resource management, real-time job routing, and the underlying stack used for model execution.
I’ll also demonstrate running an AI model locally, sharing it within a small peer group, and scaling it into a shared public pool — all with minimal setup. The presentation will emphasize how this approach can democratize AI compute and enable a community-powered alternative to centralized cloud infrastructure.