Remix.run Logo
rootlocus 4 hours ago

2x RTX3090 are around $4400. Without any electricity costs or other parts, that's 3.6 years of $100/m claude.

overgard 3 hours ago | parent | next [-]

Assuming the $100/m claude subscription is still around in three years.

reddalo 2 hours ago | parent [-]

[dead]

freetonik 4 hours ago | parent | prev | next [-]

That's also years of top tier PC gaming, if you're into that.

augusto-moura 4 hours ago | parent [-]

2x RTX3090 is extremely overkill for gaming, you can run any released game on earth on ultra for much less

drnick1 3 hours ago | parent | next [-]

1x RTX3090 is absolutely not overkill for gaming however. Nowadays it's barely enough to get 60FPS in 4K in some recently released games. But the shocking part is that my 3090 is still probably worth as much as when I bought it about 4 years ago.

overgard 3 hours ago | parent | prev | next [-]

Having a second card doesn't really work well for gaming.

googletron 3 hours ago | parent | prev [-]

what?

kakacik 3 hours ago | parent [-]

AFAIK nvidia cards dont work in tandem (aka sli in the past) very well these days. So that aint true.

Also, 2 gens old means bad performance at ray tracing, abysmal path tracing if at all. Pretty sure it can't run smoothly CP2077 in native 4k without dlss upscalers with all on ultra.

himata4113 3 hours ago | parent [-]

You can have the 2nd card as an offload for upscaling, frame generation and whatnot.

irishcoffee 2 hours ago | parent [-]

When I'm not running models I use the 2nd one in a pass-thru configuration to a windows vm for various things, usually gaming.

horsawlarway 4 hours ago | parent | prev | next [-]

Yes, today is not a great time to purchase hardware.

When I bought, I paid $850 a piece. And I needed one anyways for the gaming I was going to do.

My guess is the next good time to buy is going to be 24-36 months from now, depending on how the AI bubble goes.

---

I'll add to this, I personally don't like Apple hardware (not so much related to the hardware as their company philosophy) but their machines with unified memory (or AMDs latest unified memory offerings) get pretty equivalent speeds to my 3090s, and are probably a much better modern entrypoint to local llms.

There's a reason the joke is that Silicon Valley software devs bought up all the Mac minis for OpenClaw.

You can get a 48gb unified RAM M4 pro mac mini for ~2k. If you're not going to do much else with the machine, it's what I'd pick as my budget inference device right now. Spend a year of claude now, get ~150tok/s for the next decade (plus) for ~free.

If you want more capable and are willing to spend a little more, go with the newer Ryzen AI Max+ 395 machines.

You'll spend less on power too.

My last suggestion would be to go buy an RTX3090 at this point. You can do a lot better for a lot cheaper.

tracker1 2 hours ago | parent [-]

If you're willing to go the AMD route, the AMD Radeon Pro R9700 definitely looks interesting for the price compared to NVidia.

felooboolooomba 5 minutes ago | parent [-]

Can we also run LLMs on Radeon?

jmuguy 3 hours ago | parent | prev | next [-]

Or a really excellent experience playing Satisfactory with the settings cranked up, which is priceless.

tripleee 3 hours ago | parent | prev | next [-]

Christ GPU prices have gotten crazy

How do AMD cards perform with LLMs? A 9070 is sold for ~$600 and has 16GB VRAM

overgard 3 hours ago | parent | next [-]

In my personal experience, I wouldn't bother with 16GB cards for coding -- the useful models are _slightly_ too large to work at any reasonable speed

lambda 3 hours ago | parent | prev [-]

That should do pretty well. Memory bandwidth is the biggest bottleneck for token generation, at 644 GB/s you should be able to do pretty well on a 9070, while prompt proessing is more compute bound and Nvidia tends to have the edge there.

16 GiB won't fit you much, so you'd probably want at least 2x, and preferably 3x of those, and then you need a motherboard, power, etc. that can handle that.

tracker1 2 hours ago | parent [-]

You can get an R9700 with 32gb vram for ~$1200-1400 depending on where you live, which is probably a better option for AI use than 2x 9070(xt)

lambda 37 minutes ago | parent [-]

Yeah, definitely.

nyrikki 4 hours ago | parent | prev | next [-]

You can get 60tps with three 1080tis and the sparse model, and I bet two 16gb 5060tis would do the same for ~1200. One 3090 is enough for a useful system, even on an old am4 host.

flowerthoughts 3 hours ago | parent | prev | next [-]

In 3.6 years, chances are they are still worth $3k. Unless some new chip fab pops up that can spam the chip market. Even if the AI bubble bursts, I doubt we'll see high-RAM GPUs sell off.

sieabahlpark 4 hours ago | parent | prev [-]

[dead]