Earlier quoted context omitted.
The application development APIs, ie: https://developer.apple.com/documentation/technologyoverview...
Any serious LLM work isn't going to use that. They'll use Metal GPU. No one is going to inference using the NPU on a Mac. OP said "work stations" which is implying Macbook Pros and Studios.
> Any serious LLM work isn't going to use that.
That’s my point.
One would expect the platform owner (especially one where they own both the hardware AND software) to provide a reasonable / easy path to using LLMs if they are going to provide a framework for doing so. But Apple can’t because of how slow they ship updates