Actually not 100% true, you can offload a portion of the model into ram to save VRAM to save money on a crazy gpu and still run a decent model, it just takes a bit longer. I personally can wait a minute for a detailed answer instead of needing it in 5 seconds but of course YMMV

There's plenty of open source models that don't really have any restrictions, you just have to host them yourself (which you can do on your own computer if you have a decent gpu)

for example: mixtral 8x7b

just use koboldcpp or something similar to run the GGUF files and you're good

Also, there are literally people who are doing this as of 3 MONTHS AGO

Huh, I wonder what OP is using......

Very cool modern OS

ItS ThE FaULt Of ThE GPu MaNuFaCTUrErS

I can't think of a more useless comment than to split hairs on what "bricking" means to a beginner when you can't even boot your system if you fuck this up

ah yes, the millionth person recommending mint as a beginner distro because they used it 10 years ago, ignoring the fact that it completely bricks your system if you DON'T REMOVE AND REINSTALL YOUR GRAPHICS DRIVERS WITH EVERY UPDATE

use something with a sane and easy to use package manager that just works like nobara, fedora, endeavor, literally anything else