Web browser company Opera announced today that it will now allow users to download and use large language models (LLM) locally on their computer. This feature will be implemented for the first time in opera one users receiving stream updates from developers and will allow users to select from more than 150 models from more than 50 families.
These models include Llama de Meta, Gemma de Google and Vicuña. The feature will be available to users as part of Opera’s AI Feature Drops program to allow users early access to some of the AI features.
The company said it is using the open source Ollama in-browser framework to run these models on your computer. Currently, all available models are a subset of the Ollama library, but in the future, the company is looking to include models from different sources.
Image credits: Opera
The company mentioned that each variant would take up more than 2GB of space on your local system. So you have to be careful with your free space to avoid running out of storage. In particular, Opera does no work to save storage while downloading a model.
“Opera has for the first time provided access to a large selection of third-party local LLMs directly in the browser. They are expected to reduce in size as they become increasingly specialized in 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 multiple models locally, but if you want to save space, there are many online tools such as Poe from Quora and HugsChat to explore different models.
Opera has been playing with AI-powered features since last year. The company launched an assistant named Aria located in the sidebar last May and introduced it in the iOS version in August. In January, Opera said it was building an AI-powered browser with its own engine for iOS, as the EU Digital Market Laws (DMA) asked Apple to remove the mandatory WebKit engine requirement for mobile browsers.