Document how to run local Inference, for the subset of models that support it

i.e. a how-to guide (or set of guides) on how to use [TFJS](https://github.com/tensorflow/tfjs) or [onnxruntime.js](https://onnxruntime.ai/docs/get-started/with-javascript.html) (or other alternatives) on either client or server JS

see those Twitter threads for instance:
- https://twitter.com/jason_mayes/status/1633858881809186816