Opera Launches WebAI Web Standard, Enabling AI Models to Run Locally in the Browser
Opera has launched a new web standard called WebAI, allowing users to run AI models directly in the browser without relying on cloud services. The standard is not tied to any specific model; taking Google's open-weight model Gemma as an example, on Mac it also supports calling Apple's on-device foundation models. It is currently available as an early preview in Opera One and requires users to enable it manually, with Opera GX and Opera Neon to follow. Opera says its advantages lie in privacy protection and no subscription, but actual performance depends on the device's hardware configuration.
Why read this
AI score 60
Opera has turned running local models into a browser standard and provided an early preview, so readers can use it to judge what on-device AI deployment will look like and the hardware trade-offs involved.
Topics
Body · AI translation
Opera Launches WebAI Web Standard, Supporting Local AI Model Deployment in Browsers
English text is being prepared.
English text is being prepared.
Opera said WebAI is designed to be compatible with a variety of AI models. The company cited Google's Gemma as an example. This is an open-weight model released by Google, first published two years ago. Opera also said that on Mac computers, WebAI supports calling Apple's on-device foundation models.
Opera emphasized that WebAI is not tied to any specific model, but is built for a variety of open-weight AI systems. The project stems from Opera's earlier work on bringing locally running large language models into the browser.
Currently, Opera has launched this AI feature in an early preview version in its flagship browser Opera One. The company said that Opera GX, a browser for gamers and live streamers, and Opera Neon, a browser capable of using AI agents to perform tasks, will also receive the same feature soon. Users need to actively opt in to WebAI to use the related features.
Open-weight models bring many benefits to users. First, such models can usually be downloaded and used for free. Second, their underlying model weights are made public, giving developers greater freedom to customize the models according to their own needs. However, unlike fully open-source software, open-weight models may still be subject to certain restrictions on use and modification.
Opera said privacy protection is also an important advantage of WebAI. Users can use AI features without having to send personal information to corporate servers, and without paying for cloud AI service subscriptions.
Opera said in its announcement: "Developers can add AI features to their products without deploying AI infrastructure or paying for each request. Users do not need to purchase AI subscription services, information processed by local AI stays on the user's own device, and users can continue to control AI on their computers."
Opera also said that with WebAI, users can directly generate text, classify content, and understand the relationships between different pieces of information in the browser.
English text is being prepared.
Locally running AI models offer another option, because all processing is done on the user's own device rather than on corporate cloud servers. This does not mean all privacy risks can be eliminated, but it does give users more control. Therefore, Opera has for years made digital privacy protection one of the main selling points of its products.
However, running AI models locally also involves certain trade-offs. Because the models need to directly use the computing resources of the user's computer, this may increase hardware load and thereby affect device performance. Opera cautions that the actual performance of WebAI will depend on the hardware configuration of the user's device.