llamaperf

GLM-5.2

on NVIDIA RTX 5090 · llama.cpp

Tone: mixedNVIDIA hardware
Aug 28, 2026
System RAM
192 GB
VRAM reported
32 GB

Summary

User reports running GLM 5.2 on a system with 5x RTX Pro 6000 and 1x RTX 5090. User reports 98-99% task completion. User notes high heat and cost.