Why it matters
Gives practitioners a concrete, hands-on path to running models on their own infrastructure as a real alternative to paying per-token for hosted APIs.
The tokenmaxxing angle
Self-hosting and virtualizing open-source LLMs is a direct cost-avoidance strategy against per-token API spend, exactly the tradeoff tokenmaxxing covers.
From the organizers
Page names speaker Tony Bubbins, a Senior System Engineer and Platform Architect, covering virtualization, self-hosting LLMs, and quality-of-life UX tool demos; 49 RSVPs yes.