Modern web applications rely heavily on cloud-based AI, but this comes with trade-offs: latency, cost, and privacy concerns. What if powerful AI models could run entirely inside the browser, even without an internet connection?

In this talk, we’ll explore WebLLM, a cutting-edge approach to running Large Language Models directly in the browser using WebGPU. You’ll learn how offline-capable chatbots can be built using JavaScript: no servers, no API keys, and no data leaving the user’s device.

This session is designed for web developers curious about the future of privacy-first, offline-ready AI experiences on the web.