Opera introduces a new web standard to let users deploy AI locally in their browser

Opera has unveiled WebAI, a new web standard that allows users to run AI models directly in the browser without relying on cloud infrastructure. The standard supports a variety of open-weight models, including Google's Gemma and Apple's on-device foundation model on Macs, and is not tied to any specific model. It is initially available as an early preview in Opera One, with Opera GX and Opera Neon expected to follow, and requires user opt-in. Open-weight models are free to download and use, with publicly available weights that give developers greater customization freedom, though some restrictions remain. A key advantage is privacy: local processing means personal data stays on the user's device rather than being sent to company servers, eliminating the need for AI subscriptions. The standard enables text generation, content classification, and information relationship understanding directly in the browser. However, running AI locally demands more from a user's hardware, and performance will depend on the device's capabilities.

(Source：TechCrunch)