Unfortunate you don’t have multimaterial capability, neither do I :p
At my work however, I get to use PLA supports with TPU, which barely sticks enough to be support material but allows me to run it as if it were dissolvable support and is an actual treat to remove
Kinda lowballed and got an RX6600, honestly pretty chuffed how well it runs LLMs compared to my 2060. Still last gen, but admittedly I’ve only been playing factorio as of late, and Im not so graphics focused
I had an R5 1600x basically since it released, and I appreciate the socket lasted so long. I might as well go full AMD at this point, you’ve convinced me
555 drivers have given me a couple issues on my main PC, I’ve heard of some issues with newer cards but I figure its just a matter of time before better drivers. I haven’t had to touch pci passthroughs yet and I was unsure if theres more a challenge on server hardware with Nvidia, but it sounds like I’ll be happy to have CUDA
Xeon E5-2640 unfortunately does not, though still an upgrade of what I have now. Stream limit seems entirely configurable, so that will be just a matter of stress testing.
Won’t lie I always forget about all the new CPU hardware acceleration after using decade old hardware for so long 😅
I didn’t even realize CUDA had a weight on LLMs, thank you!
There is Friendica… yeah the name doesn’t roll of the tongue, and I only remember just for this comment… no shade to it