Remix.run Logo
CamperBob2 2 hours ago

Consumer motherboards can still make sense even if you leave some performance on the table. Running an actual 8x GPU server is not something you'd want to do in an apartment. Imagine the old Lucasfilm "THX" trailer where an unearthly-sounding foghorn whine rises to a sweeping crescendo at reference level, only without the decay at the end.

At the time he put this rig together, there weren't a lot of open-weight LLMs that could run well on 6x48=288 GB, so it probably wasn't a huge loss. There still aren't, really.

Right now I'm in the process of cramming Blackwell cards into an old DDR4-based Milan server, where the important thing is to be able to run large models at all. The GPU fans alone burn over 400 watts at full throttle.

storus 2 hours ago | parent [-]

Did you think about Max-Q cards? 300W and they aren't that noisy either, 14% lower perf than non-Max-Q card.

CamperBob2 2 hours ago | parent [-]

That was an option, but having decided on a true server chassis for other reasons, it made sense to use server-edition cards to take advantage of all those fans. I downclock them to 300W anyway for longevity, but it's nice to have the option to go to 600W if needed.

The server is going to live in the garage, so I'm not that concerned with noise. But I had no idea what to expect when I flipped the switch for the first time. It sounds like something out of the Book of Revelation. No way, no how could something like this be used in an inhabited area.