[nok22kon]

the same argument was made 2 years ago: "in 2 years we'll be able to run GPT-4 level models on an expensive laptop, most people will be using this instead of the fancy cloud models".

we are there, Gemma4/Qwen3.6 are GPT-4 level models runnable on a fancy laptop.

but expectations shifted, nobody wants a GPT-4 level model anymore

[jijijijij]

Well, then you also have to assume higher expectations put on commercial offers raising operational costs. So, your objection really is a moot point.