A user shares their home lab setup with four GeForce 3090 GPUs and 192GB of DDR5 RAM overclocked to 5600 MHz. They run GLM5.2 at 7 tera-giga (tg) as a planner, MiniMax 2.7 at 45tg in VRAM for coding, and Qwen3.6 27B at q8 for testing, all on consumer-grade hardware due to cost considerations.
GLM5.2 runs at 7tg on 4x 3090s with 192GB DDR5 on budget build
from English