points by KeplerBoy 4 days ago | 0 comments
The RTX Spark is also sold in a mac mini form factor. That's pretty well suited for home inference.
[–] barrkel 4 days ago
[–] jacquesm 3 days ago
That's slower than I would have expected for the RTX 6000, do you have figures for say Qwen 3.8 27B? That model fits completely on the card, that should push it a lot further.
[–] barrkel 3 days ago
I'm pretty certain I can get it to go faster by caching experts and whatnot (with experimental llama.cpp branches), but that would consume a lot more VRAM and it's fast enough as it is for playing around with, and I can leave it always loaded. It's like 50% CPU inference, with a few layers + router + kv cache on the GPU.
[–] jacquesm 2 days ago
Unused VRAM is a crime now, I heard ;)
I meanwhile, run my ridiculously OP workstation class hardware as a server - 9995wx, 768GiB, rtx pro 6000 w/ 96GiB vram - at home, and my Asus ZenBook is light, cool, and long-lived.
Runs GLM 5.3 flash at 35 tok/sec while consuming only 15 GiB VRAM, and I can run a lot more stuff on there alongside.