Hmmm, 2-3 high end GPUs implies it's likely not very far off from mainstream. Maybe runnable on the average device within 10-20 years... perhaps even sooner if the model/software can be optimized?
ChatGPT prompt: What's the difference between a component and subcomponent?
A component is a self-contained unit of functionality, often in the form of a class or object, that represents a piece of an overall system or application. A subcomponent, on the other hand, is a smaller, simpler component that is used as part of a larger component. A subcomponent is typically used to break down a larger component into smaller, more manageable pieces, and is often used to create reusable building blocks for larger components. In other words, a subcomponent is a component that is used by another component.
it seems a bit long for achieving just running your own AI models locally, given it seems to be largely a question of vram and that you already _could_ do it today with a handful of graphic cards.
20y ago we had the GeForce Ti4400, current graphics cards now come with 100x the vram and 50-60x the bandwidth.
That's one hell of an assumption. Many of my Russian friends were absolutely certain they'll be alive and well for at least the next 20 years not that long ago.
Looks like FLOP/s per $ are doubling every ~3 years for high end cards, and 10x in ~10 years. So probably not that far off for desktop users.
https://www.lesswrong.com/posts/c6KFvQcZggQKZzxr9/trends-in-...