Professional GPU
H100 80GB SXM
The GPU most large AI labs actually train and serve on today. 80GB of HBM3 memory per card, with NVLink for true multi-GPU clustering. This is the building block behind the DGX systems below.
80 GB
GPU memory — how large a model (in parameters) can be loaded and run.
700 W
Power draw — equivalent to 0.58 average homes running around the clock.
$30,000
Price for this unit as configured.
1
GPU in this unit.