LocalLLaMA

1 readers

1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 10 months ago

MODERATORS

communick@poweruser.forum

Anyone spend a bunch of $$ on a computer for LLM and regret it? (alien.top)

submitted 10 months ago by parasocks@alien.top to c/localllama@poweruser.forum

22 comments fedilink hide all child comments

Curious if anyone got the whole rig and realize they didn't really need it etc

you are viewing a single comment's thread
view the rest of the comments

[–] jubjub07@alien.top 1 points 10 months ago (1 children)

I built my 2x3090 with parts from eBay... MB (x299 Giga), i9 CPU, 64G RAM and 2 3090s... I did spring for a new, heavy duty PS and case with big fans.

All in, I spent about $2k.

System runs 70B models like Llama-2-70B-Orca-200k just fine at 11 T/s...

I feel like there's not a ton of downside - I think the 3090s will be valuable for a while yet, and that's over half the value of the system.

Having the hardware right here means I can have thing running all the time - when I read about a new model, I can download, play, etc. in minutes. Spinning up a runpod feels frustratingly slow to me. I went that route for a while, but found that the friction involved meant I tried fewer things. Having a system that might be slower, but is always available just works for my way of working.

So no "regerts" here.

[–] Infamous_Charge2666@alien.top 1 points 10 months ago

lol i have just finished identical system just a tad stronger..x299x mobo, i9- 10980 XE, 2 x 3090TI, 256gb. 72TB HDD (WD reds) + 4TB Samsung 990 Pro for 3.5k