Professional GPU
A100 80GB
A previous-generation datacenter GPU still widely used for inference. 80GB of HBM2e memory and NVLink support mean multiple A100s can be pooled into real, high-bandwidth clusters for serious models.
80 GB
GPU memory — how large a model (in parameters) can be loaded and run.
400 W
Power draw — equivalent to 0.33 average homes running around the clock.
$10,000
Price for this unit as configured.
1
GPU in this unit.