a way to check if browser can run a model or not

[RTLer]

Please make sure that this is a feature request. As per our GitHub Policy, we only address code/doc bugs, performance issues, feature requests, and build/installation issues on GitHub. tag:feature_template

System information

• TensorFlow.js version (you are using): 3.9.0
• Are you willing to contribute to it (Yes/No): yes

Describe the feature and the current behavior/state.

Running models on devices with low resources can lead to a bad user experience or break site stability.

In my project, I ran Blazeface to help users position themselves in front of the camera.
Still, skipping the model and doing a low-performance route could have been a better experience for some testers.

Will this change the current API? How?

No, it's a new API.

Who will benefit from this feature?
sites that need to fall back to a low-performance mode or turn off TFjs for low-resource users.

Any Other info.
my idea is to run a dummy model or tasking calculation to score the resource.