[btbuildem]

I think it's silly to go for a laptop form factor. Last fall I put together a workstation with two second-hand 3090s in it (paid $850CDN each, now the best I can find is $1200). With 48GB VRAM it's reasonable - and I've been using Qwen 3.6 27B for various tasks around building KGs from text corpora / reasoning about them.

I've ran comparisons against everything that's available on OpenRouter (well, as of few weeks ago), and for $0/tok, the local 27B Qwen can't be beat. Sure, it's slower, and yeah, the office is a few degrees warmer than it ought to be -- but nobody can pull the plug, nobody is watching over my shoulder, and the results are on par with SOTA.

Can't wait for a similarly sized Qwen 3.7 - from what I've seen so far, it's a leap ahead of the previous version.

[Gigachad]

I think it still makes sense to wait. Hardware is currently hyper expensive and cloud models are subsidized. Waiting 2 years or so once memory prices have dropped and datacenters start wanting a profit would get you a usable setup that's more economical.

[whichquestion]

How much electricity does running your local models take?

[btbuildem]

I throttle the GPUs to ~280W each (my cooling solution is insufficient to run them full tilt), and so at peak usage I show a ~1200VA draw. Electricity is relatively cheap here, so the main disadvantage of the at-home setup is having the equivalent of a small space heater running in the summer.