Post by @Orygin@sh.itjust.works

@Orygin@sh.itjust.works

2026-10-25 19:38 UTC

Won’t happen unfortunately. Unless you want to run a 1U with 6 GPU, requiring a custom water-cooling system, and which sips like 10kW/h of electricity while idle. It’s all integrated hardware born to be trash. The ram, cpu and GPU won’t be usable on consumer hardware without hard modifications.

Replies (3)

@mindbleach@sh.itjust.works 2026-10-25 23:13

Local models are only months behind. The primary utility of comically large networks is a wider search space for the tiny fraction of weights that really matter.

Open ##5246141
@SapphironZA@sh.itjust.works 2026-10-26 00:23

Nothing that some We also don’t need frontier models. The type of models that run on $5000 Mac studios can do today what the frontier models did 1 year ago. We just need to Mac studio class hardware to come back to $2000 where it used to be. Also, do not underestimate the ability of Chinese BGA rework shops from being able to salvage AI chips and install them on board that will fit in standard hardware. They proved they could do it with the Crypto only chips, they will figure it out for the AI chips if the supply is there. The main reason these units use water cooling is for deployment density.

Open ##5246771
@SapphironZA@sh.itjust.works 2026-10-26 00:42

1 of those GPUs can probably run 90% a small team would need, so you don’t need the full thing. That’s about 600w of draw and 150w idle. Or about the same as a 5090. You don’t need exotic power or cooling for that.

Open ##5247025