There are multiple very good reasons to host your own AI models. Those reasons are not going away with time, but rather multiplying.
It's about capability:
1. Do you have the right hardware? Most people don't and hardware has just exploded in price. One of the RAM makers and also AMD have said they will focus on data centers, which will only make things worse.
2. Do you have the know-how? It needs to be as easy as installing and using Chrome.
3. The end result needs to be directly as usable as ChatGPT.
Fairly local LLMs fail all 3 points.
However, Apple is already including LLM models automatically with even iOS that can be queried for historical facts, etc.
We need unified memory for almost everything for these types of setups to be usable and we also need to standardize LLMs, if everyone wants to run their own LLM locally, that will probably be untenable for decades. We probably need new DRAM tech (3D RAM?).
Hardware prices need to go down a lot, and we're probably 5+ years away from that. Not only do prices need to go back to where they were, they need to become even lower. So we're probably 10+ years away from usable good enough local LLMs for the masses.
It's going to be an ugly decade from a hardware economics point of view. The potential is endless, but the way there is hard.