Hello guys, hoping you're doing fine! I was wondering, for users with 4x-8x 6000 PROs (so between 384 and 768GB VRAM), how are bigger models working for you? I have planned to either jump to 4 or 8 from my actual system, and want to see the experiences with these lately. In theory you can run GLM 5.2 at 4 bits, but not 8 bits right? Same with Kimi 2.7, or DeepSeek V4 Pro. There is a ton of info here https://github.com/local-inference-lab/rtx6kpro/blob/master/benchmarks/results.md , but mi...