GLM-4.5-Air 106B (12B active)
on NVIDIA RTX Pro 6000 Blackwell · llama.cpp
Summary
User reports GLM-4.5-Air at about 138 tok/s on an RTX PRO 6000 96GB.
Setup is llama.cpp with Q4_K_M, measured at empty context.
The figure comes from a site of 941 measured rows, including 540 llama-bench rows the user ran on rented GPUs from an RTX 3060 12GB through an RTX 5090 and an RTX PRO 6000 96GB.