Since you obviously can’t use unified RAM, VRAM is going to make the most notable difference in locally run LLMs. But even if you do get a more powerful GPU, unless you drop thousands of dollars on one with more VRAM (on top of other components you may need to upgrade as well), you are, unfortunately, not going to have anything comparable to frontier cloud models.

The $20 a month is going to be far more affordable. Again, this is all by design so that you are locked into cloud models once you get hooked onto LLMs.

I’m sorry, this seems cool, but the AI-generated comparison chart is illegible and off-putting.

The comments section on that article truly was a ride.

I think most don’t even try, which I don’t blame. I had to essentially put in a business proposal for my work Linux computer.

This reminds me of an old couple who lives about a block or so away from me. They have 2 lawn cameras that photograph every car and every pedestrian that goes past their house. And I don’t think a single crime has been reported in our quiet neighborhood in probably over a decade.

And CRTs are unbelievably heavy in comparison, making them a bitch to move at all.

Totally not vibe-coded at all

And it’s always something super low, like 5%.

For those wondering what QBJ3 is (because I didn’t know.)

Quake Brutalist Jam III is a megalithic community project more than a year in the making. It features an entirely new arsenal, a set of new monsters, new powerups, and a complete visual overhaul of Quake’s existing roster.

Mmmmm sloppy

I’m not convinced my cat doesn’t support facism.

Not sure what he did wrong

Ah, yes, the only thing that makes dog barking more annoying is when the human is barking too.

“Bad Reggie! No! No!”

No hard feelings, but I am obligated to post it when relevant :P

Undertale.

It’s inherently uncreative and it’s even more likely to produce same-y material when you 1. Don’t give it a specific art direction and 2. Use the same generic models everybody else is using (a result of Googling, “AI art generator”.)

Which, in fairness, there are plenty of. I have seen 2 presentations this week at work where they were 1. Obviously AI-generated and 2. Obviously not proofread or changed at all.

Just like you, I’m crammed it in :P

I built two of these, one in 2021 for a client and another in 2023 IIRC, back when SSDs and RAM weren’t outrageously priced, so it’s got an NVMe m.2 SSD and 64 GB of RAM.

It’s got an AIO cooler, and I don’t think anything other than that or a stock fan would fit in there. It had a 3060 12 GB but it has died :/ so it’s currently got a 2060 SUPER, which doesn’t fit as well (mainly because the power port points towards the front of the case instead of up.)

With the discrete GPU and AIO cooler, I wouldn’t have been able to fit a SATA SSD in there.

Both of these were far from the most painful builds I’ve done.

I have that exact same case for my work computer!