Local Models: How to Run AI in the Browser
summary
The talk explains how to run local AI models directly in the browser using WebGPU to embed AI agents into UI without increasing server load. It surveys libraries that support WebGPU (for example, Transformers.js and @mlc-ai/web-llm), compares alternative browser runtimes (WebAssembly, WebNN), and gives usage examples and application prospects, including in space-related projects.
AI-written summary · about
chapters (10)
- 0:00Introduction to local models
- 3:11Why use local models
- 7:27Data processing methods
- 11:01Replacing cloud with local models
- 13:27Optimizing models for browser
- 17:43Browser implementation
- 23:06Local models pros and cons
- 24:29When to use local models
- 26:15Use case examples
- 28:03Q&A
related talks
31mBringing and Running AI Agents in the Browser
46mThe Ultimate Guide to Browser-Based AI: Privacy-First, Offline-Ready and Future-Proof
41mEscaping the Cloud: High-Performance AI in your Browser
24mWeb Apps of the Future With Web AI
21mUnlocking Client-Side AI in Your Web App
45mPrivacy-First In-Browser Generative AI Web Apps
01mJavaScipt & AI
02mDiscover Web AI: Client side Agents, Gen AI, and machine learning in the browser