This is only possible because the stock market is a fucking Ponzi scheme

And don’t forget tech “reviewers” like Linus who badmouth Nvidia and then only show their fucking GPUs in every video that isn’t an AMD benchmark

Nvidia’s been treating gamers like shit since they killed 3dfx and idiots still fanboy for them… If it hadn’t been supported by these idiots for all these years we probably wouldn’t have reached this situation

Not OP, but I still haven’t found anything worthy of replacing (the now radioactive) Nova Launcher

Idk if it’s still the case but phone memory used to go bad over time, reducing in size and speed with usage

Is this the Gavrilo Princip moment of the semiconductor wars?

Just follow whatever’s trending now yesterday.

Piracy is the only moral choice when it comes to large services

If you look at it right now the only reason you don’t have home AI as a commonplace solution is because the manufacturer has chosen not to sell it to you.

And memory shortage. By buying up all RAM they ensured that you can’t run much more than lobotomized models.

Other manufactures will arise then. Won’t be quick, won’t be painless, but the US is not the whole world.

I mean I do bring the phone into the bathroom to listen to music, but I use it with a bluetooth speaker and it stays on the sink. Why would you even bring it inside the shower? Capacitive touch screens work like shit when wet.

LLM = AI
AI ≠ LLM

And talk to who? You (and I) and the 0.001% can ham it up, but the rest of the world will be living in a different bubble.

And just talk btw, no bandwidth for anything else

Yeah I was lucky to buy a 6900XT when it was near the lowest price, so I sold that and added a couple hundred for the 7900, seemed like a good future-proofing move, given the times we’re living in.

I think Apple silicon is faster than my generation of Ryzen, but the newest (Strix something?) with the LPDDRGGFASEWARGH5 memory should be faster yet. Of course buying all that memory right now would be quite painful.

So I have a framework laptop with ryzen ai cpu that uses 48gb of shared ram, and it does run Q4 llms fine enough, but I’m not sure it compares to a real GPU.

On my desktop I have an RX 7900 XTX but I’ve only dabbled in image generation so far, so right now I couldn’t really tell you the difference.

Well it works anyway even with a bit of occupied vram, but you could also buy a cheap videocard to use as an output. I have small intel card like that in my server for jellyfin transcoding, I think I paid 60€ for it, it hardly uses any power

If your MB has onboard graphics, maybe you could mask the GPU and just pass it off to a container running the LLMs I guess

Yeah, I’m glad I took the time to set up a separate VLAN for this. It wasn’t easy on my MikroTik router (nothing ever is with those), but it’s worth the effort.

it has to share VRAM with the DE. Maybe I’ll set it up for remote development from my laptop instead to free up VRAM.

eh, just systemctl isolate multi-user.target

Might be nice if you’re used to it