Opera allows users to download and use LLMs locally

Web browser company Opera today announced that it will now allow users to download and use extended language models (LLMs) locally on their computers. This feature is rolling out first to Opera One users who receive updates from the developer feed and will allow users to choose from over 150 models from over 50 families.

These models include Llama from Meta, Gemma from Google and Vicuna. The feature will be available to users as part of Opera’s AI Feature Drops program to allow users early access to certain AI features.

The company said it uses the open source Ollama framework in the browser to run these models on your computer. Currently, all available templates are a subset of Ollama’s library, but in the future the company plans to include templates from different sources.

Image credits: Opera

The company mentioned that each variant will take up more than 2 GB of space on your local system. So you need to pay attention to your free space to avoid running out of storage. Notably, Opera doesn’t do any work to save space when downloading a template.

“Opera offers for the first time access to a wide selection of third-party local LLMs directly in the browser. They are expected to decrease in size as they become more and more specialized for the tasks at hand,” Jan Standal, vice president of Opera, told TechCrunch in a statement.

Image credits: Opera

This feature is useful if you plan to test different models locally, but if you want to save space, there are plenty of online tools like Poe and Quora’s HuggingChat to explore different models.

Opera has been playing with AI-based features since last year. The company launched an assistant called Aria located in the sidebar last May and introduced it to the iOS version in August. In January, Opera announced it was building an AI-powered browser with its own engine for iOS, as EU Digital Market Laws (DMAs) required Apple to remove the mandatory requirement for WebKit engine for mobile browsers.


Back to top button