Apple added (a while back) what they call a “Neural Engine,” which is hardware dedicated to efficient execution of ML workloads.
https://en.m.wikipedia.org/wiki/Apple_A11
They have been refining it ever since. I would not be surprised if they made advancements in both the hardware and software used for local GAI.
Another one people might be interested in is Lapce. Seems to be the same thing as Zed, but has a Linux build available. https://lapce.dev/