Rig report
NVIDIA B200 (192GB)
192.0 GB memory · 8000 GB/s · 20 of 22 tracked models fit
Best model it can run
Hunyuan Hy3 (MoE)Runs great
Q3_K_M · 128.9 GB · 223–334 tok/s · capability 88/100
Fastest that fits: Llama 3.2 1B at 316–474 tok/s
Have a NVIDIA B200 (192GB)? Add your real benchmark → to sharpen these numbers for everyone.
Estimates from device specs and model architectures, refined by community benchmarks. See the methodology.