Firebase ML is deprecated and will be shut down on June 15, 2027.

Projects that didn't previously use it can no longer start using it, and existing projects should begin migrating away.

If you're using Firebase ML to host TensorFlow Lite models for local inference, migrate your apps to use Cloud Storage instead.
If you're using Firebase ML to call Cloud Vision APIs, either migrate your apps to use Firebase AI Logic to analyze images, or modify your apps to directly access the Cloud Vision API endpoints.

Deploy and manage custom models

To deploy a TensorFlow Lite model:

Open the Firebase ML Custom model page in the Firebase console.
Click Add custom model (or Add another model).
Specify a name that will be used to identify your model in your Firebase project, then upload the TensorFlow Lite model file (usually ending in .tflite or .lite).

After you deploy your model, you can find it on the Custom page. From there, you can complete tasks such as updating the model with a new file, downloading the model, and deleting the model from your project.

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 2026-08-19 UTC.

Deploy and manage custom models Stay organized with collections Save and categorize content based on your preferences.

Deploy and manage custom models