I’m pretty sure you can load the model using RAM like another poster said. Here’s a used server under $600 that could theoretically run it: ebay.
Comment on Smaug-72B-v0.1: The New Open-Source LLM Roaring to the Top of the Leaderboard
cm0002@lemmy.world 4 months agoOh if only it were so simple lmao, you need ~130GB of VRAM, aka the graphics card RAM. So you would need about 9 consumer grade 16GB graphics cards and you’ll probably need Nvidia because of fucking CUDA so we’re talking about thousands of dollars. Probably approaching 10k
Ofc you can get cards with more VRAM per card, but not in the consumer segment so even more $$$$$$
girsaysdoom@sh.itjust.works 4 months ago
brick@lemm.ee 4 months ago
You would want to look for an R730, which can be had for not too much more. The 20 series was the “end of an era” and the 30 series was the beginning of the next era. Most importantly for this application, R30s use DDR4 whereas R20s use DDR3.
RAM speed matters a lot for ML applications and DDR4 is about 2x as fast as DDR3 in all relevant measurements.
If you’re going to offload any part of these models to CPU, which you 99.99% will have to do for a model of this size with this class of hardware, skip the 20s and go to the 30s.
kakes@sh.itjust.works 4 months ago
Afaik you can substitute VRAM with RAM at the cost of speed. Not exactly sure how that speed loss correlates to the sheer size of these models, though. I have to imagine it would run insanely slow on a CPU.
Infiltrated_ad8271@kbin.social 4 months ago
I tested it with a 16GB model and barely got 1 token per second. I don't want to imagine how long it would take if I used swap instead.