Run LLM inference on Cloud Run GPUs with Hugging Face Transformers.js

The following codelab shows how to run a backend service that runs the Transformers.js package. The Transformers.js package is functionally equivalent to the Hugging Face transformers python library together with Google's Gemma 2 model.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025-08-06 UTC.

Run LLM inference on Cloud Run GPUs with Hugging Face Transformers.js Stay organized with collections Save and categorize content based on your preferences.