in practice everyone who wants to do ML at home buys nvidia and pays the premium
I remember CUDA being much more buggy back then but it still worked pretty good.
Back then AMD wasn't considered a real competition for ML/AI hardware.
Glad as always to see more competition in the market to drive innovations. AMD seems to be letting larger VRAM onto consumer cards, which is nice to see, just hope the AI/ML experience can get better for their software ecosystem.