Opera is now the first leading browser with built-in local LLMs

Opera now becomes the first major browser to offer built-in access to local AI models.

Starting today, the Oslo-based company is introducing experimental support for 150 variants of local Large Language Models (LLMs), covering approximately 50 families. These include Mixtral from Mistral AI, Llama from Meta, Gemma from Google, and Vicuna.

The introduction of built-in local LLMs come with a series of advantages, according to Jan Standal, VP at Opera. 

“Local LLMs allow you to process your prompts directly on your machine, without the need to send data to a server,” Standal told TNW. “Adding access to them in the browser allows for easier access to local AI and gives our users the ability to process their prompts locally, in full privacy or even offline.”

The <3 of EU tech

The latest rumblings from the EU tech scene, a story from our wise ol’ founder Boris, and some questionable AI art. It’s free, every week, in your inbox. Sign up now!

Another benefit of local models is there’s no delay in communicating with external servers, which can speed up the response time.

The feature is available in the developer stream of Opera One as part of the company’s AI Feature Drops Program for early adopters. It’s provided as a complimentary addition to Opera’s native Aria AI service. Whether the built-in local LLMs will become part of the company’s main browsers depends on the responses from the early adopter community and the future developments in AI.

To test any of the available LLMs, users need to upgrade to the latest version of Opera Developer and activate the feature. Once the model variant is downloaded, it will replace Aria until users switch it back on or begin a new chat with the AI.