A Strix Halo with similar RAM is considerably cheaper. Still not cheap, mind, but performance is OK (not great) and it will run more or less the same models.
A Strix Halo with similar RAM is considerably cheaper. Still not cheap, mind, but performance is OK (not great) and it will run more or less the same models.
At least for me, it's been pretty great, but I bought my system when it was $1800, now looks like the same system is $2700 and out of stock. I still haven't quite been able to run 120B parameter models under Windows, but for Qwen Coder 30B, it works pretty darn well for my at home needs.
Yeah, they have gone up a lot since I bought mine too. I did get Qwen3.5-122b running on all-GPU (on a 128GB machine) under a minimal Arch Linux setup (I do my GUI work on a much cheaper box). It worked, but Qwen3.6-35b is performing almost as well and a lot faster.
Still cheaper than a new Mac. Maybe not cheaper than a used one.
I've certainly thought about just moving the box to Linux, but it took far to long personally to get everything running under AMD and it works 'well enough' that I don't want to make the switch. I tried playing with GAIA on it, felt a bit limited, and now have Hermes up and running, and that seems to work quite well. All the tools are changing so quickly, it's sometimes difficult to settle in on 'what's best', so I certainly can understand folks that just want to pay for a AI subscription and be done with it.