KNIME scorer node as a local API service

This is a question about deployment of an XGBoost model. We want the XGBoost scorer to respond to API requests from another program (written in NetLogo).

We have set this up in the Hub, but it takes about a second to turn around each request which is very slow and it also seemed to have arbitrarily stopped after about 1500 requests.

Is there a way to have the XGBoost scorer and the external program communicate with each other on the same computer (whether or not it uses the Hub approach)?

Thank you for any help you can provide.

@njacknis one option I know to deploy models in a high performance environment is the use of the KNIME edge server: