4× RTX Pro 6000 Blackwell on Water, and the One Card That Wouldn't Behave
1–10 of 55 posts
Re: 4× RTX Pro 6000 Blackwell on Water, and the One Card That Wouldn't Behave
#2Converting four RTX PRO 6000 Blackwell cards to waterblocks, finding a VRM choke loose on the workbench, and getting back to 41k tok/s.
Re: 4× RTX Pro 6000 Blackwell on Water, and the One Card That Wouldn't Behave
#3Is that little computer training LLMs from scratch all by itself? That must take years to get any kind of progress, given the scale of training other providers do. Where do you get the training data from?
Re: 4× RTX Pro 6000 Blackwell on Water, and the One Card That Wouldn't Behave
#4Is that little computer training LLMs from scratch all by itself? That must take years to get any kind of progress, given the scale of training other providers do. Where do you get the training data from?
[dead]
Re: 4× RTX Pro 6000 Blackwell on Water, and the One Card That Wouldn't Behave
#5Cool post. FYI you might be better off getting one big fan for your "radiator" instead of lots of little fans. Big fans don't need to spin as fast as small fans to push the same amount of air. So they run a lot quieter.
Re: 4× RTX Pro 6000 Blackwell on Water, and the One Card That Wouldn't Behave
#6I wonder whether those cards ran the model that wrote the nonsense about the forces involved.
Hint: when you have a piece of metal stuck with thermal goop to a lot of components, the force doesn’t “concentrate” on one of them. You need to detach it from each one with however much force is needed to detach it from that component.
Re: 4× RTX Pro 6000 Blackwell on Water, and the One Card That Wouldn't Behave
#7Complete side note, but I can’t work out how the author managed to mistype “at” as “Δt”.
Edit: reading fail on my part, nothing to see here.
Re: 4× RTX Pro 6000 Blackwell on Water, and the One Card That Wouldn't Behave
#8Complete side note, but I can’t work out how the author managed to mistype “at” as “Δt”. Edit: reading fail on my part, nothing to see here.
I caught that too, probably a qwen bug (;
Re: 4× RTX Pro 6000 Blackwell on Water, and the One Card That Wouldn't Behave
#9Complete side note, but I can’t work out how the author managed to mistype “at” as “Δt”. Edit: reading fail on my part, nothing to see here.
huh? the only Δt in the article is used correctly.
> With 18× 140 mm of surface, the fans run quietly and the coolant Δt across the rads stays small
Re: 4× RTX Pro 6000 Blackwell on Water, and the One Card That Wouldn't Behave
#10If you want ready, well engineered, water-cooled multi-GPU research workstations, my colleagues at https://comino.com build and sell them. Or you can purchase fitted waterblocks from them for many GPUs, and build your own.