Go to the server section, (button on left) change the port number or leave it as is, and click the "start server" button (you may need to turn on cors)
It should look like this:
assuming the port is 1234: You should be able to see the open api endpoint now: http://localhost:1234/v1/models
It should look like this:
you should be able to set any open ai base url to http://localhost:1234/v1 and give it a random api key (I like to use "lmstudio") and see the text generation working!