In 4 days JetKVM is about to release their new light models. It’s roughly $40usd if bought in a 3 pack. One is ethernet based, one is wifi based. I did the math and I can’t even build an a equivalent product for that plus postage from parts.

If you are playing around at home I suggest seeking a MoE model. You get less penalty from having less vram and offloading to normal ram. I run Qwen 3.6 quant 6 on 250k context on a 16gb vram 64gb ram ddr4 PC. I get about 31tps which is enough for my use. After a little tweaking I have put results of it’s output into Claude Pro for vetting and it hasn’t found any flaws in the simple scripts and things I’ve asked it to make. I can only run Qwen 3.8 which is a dense model and not MoE. At low quant with not as much context. It spits out accurate short context answers if that’s all you need. So I prefer 3.6. Tiel is faster but Claude picked up more errors in what I was doing. Orinith kept getting into thinking loops for me so I stopped using it. Anyway I’m just a little guy.

Which Qwen?

I think it’s pretty cool in beszel you can set it up using docker so easily and pass the disks through for SMART monitoring and not have to have an extra solution.