by "leak" do you mean that keeping a reference to MLModel instance? in our current use case, we prefer to keep this reference through the app life cycle, because MLModel.load() is very slow (~10 secs). do you mean that we need to load ML model just on demand and release the reference to the model, then reload (another ~ 10 sec) on demand whenever we need ML model?

Hi, Apple. Let me double check your guide to avoid MLModel leak? Can you load our ML model when out app launches and keep it being loaded during app life cycle? or Should we load our ML model on-demand only when user actually use it and unload as soon as user do not use it?