Puget Workstation N120-XL
A large lower workstation based on NVIDIA’s DGX Station, featuring the GB300 superchip, and built specially for AI inference with 748GB of shared memory.
Overview
A first from NVIDIA, the DGX Station is a powerhouse workstation platform built for AI development, inference, and model fine-tuning. It includes a powerful Blackwell-architecture GPU with 252GB of high-speed memory as well as an ARM-based processor with 496GB of additional memory. Those memory groups can be pooled together for running large AI models, though the CPU’s memory is a lot slower – so larger models will not run as quickly. Additional storage can be added as well, along with a discrete GPU to handle graphics output (the GB300 has no video output capability).
Not sure what you need?
Tell us your situation and one of our experts will reply within 1 business day to help configure the right computer for your workflow. If you don’t see what you are looking for here, check out our other systems for more options.