Running Inference In Web Extensions
February 3, 2025
We’ve recently shipped a new component inside of Firefox that leverages Transformers.js (a JavaScript equivalent of Hugging Face’s Transformers Python library) and the underlying ONNX runtime engine. This component lets you run any machine learning model that is compatible with Transformers.js in the browser, with no server-side calls beyond the initial download of the models. This means Firefox can run everything on your device and avoid sending your data to third parties.
With Chrome shipping experimental support for the Gemini 1.5 Nano model in the browser, accessible via an API to JavaScript, and the ability to run models in the browsers using WebLLM, ONNYX.js, tensorflow.js and other approaches, it’s exciting to see Firefox enter the chat with experimental support for inference in the browser.
We’re so excited about the promise of these technologies we’re planning a whole focused online conference on the topic for later in 2025, Inference.
You’ll get access to that (and even other live-streamed event, and all on demand videos) with a Premium Conffab membership or purchase access to the conference itself.
