For users with 4x-8x 6000 PROs, how is your experience with bigger models lately? (GLM 5.2, Kimi 2.7, DeepSeek V4 Pro) (opens in new tab)

RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink - local-inference-lab/rtx6kpro