Implementing ML Systems tutorial: Server-side or Client-side models?

Developing machine learning models is all fun and good, but after developing them you will probably be looking into deploying them into an app to use them. The question is should you put them on the client-side (which is probably the mobile) or should you put the model on a server, send the data to the server and get the results back? In this article, I am going to be discussing the trade-offs and what those 2 methodologies entail. Server-side machine learning models are the most widely-used ML systems simply because the architecture is more simple to implement. For example, you have an application running on the phone (the client) that classifies images.