The full lineup

Catalog

Every price, spec, and wattage below is a real, current, sourced number — the same figure appears everywhere this product shows up on the site.

consumer gpu

NVIDIA GeForce RTX 5090

The on-ramp: a single desktop card for prototyping with open models

$2,399
  • GPU memory32 GB
  • Power draw575 W
  • GPUs in unit1
workstation gpu

NVIDIA RTX 6000 Ada Generation

A quiet workstation card built to run flat-out, 24/7

$6,800
  • GPU memory48 GB
  • Power draw300 W
  • GPUs in unit1
workstation gpu

NVIDIA RTX PRO 6000 Blackwell Workstation Edition

The biggest single card money can buy — no server room required

$12,500
  • GPU memory96 GB
  • Power draw600 W
  • GPUs in unit1
datacenter gpu

NVIDIA H100 SXM

The GPU that started the modern AI datacenter buildout

$28,000
  • GPU memory80 GB
  • Power draw700 W
  • GPUs in unit1
datacenter gpu

NVIDIA H200 SXM

Same compute as the H100, with far more memory to work with

$35,000
  • GPU memory141 GB
  • Power draw700 W
  • GPUs in unit1
datacenter gpu

NVIDIA B200

NVIDIA's current-generation Blackwell datacenter GPU

$40,000
  • GPU memory192 GB
  • Power draw1,000 W
  • GPUs in unit1
server

NVIDIA DGX H100

Eight H100s, pre-cabled into one appliance

$380,000
  • GPU memory640 GB
  • Power draw10,200 W
  • GPUs in unit8
server

NVIDIA DGX H200

The same trusted DGX chassis, upgraded to H200 memory

$349,000
  • GPU memory1,128 GB
  • Power draw10,200 W
  • GPUs in unit8
server

NVIDIA DGX B200

Eight Blackwell GPUs in NVIDIA's current flagship server

$515,000
  • GPU memory1,536 GB
  • Power draw14,300 W
  • GPUs in unit8
rack cluster

NVIDIA GB200 NVL72

72 GPUs and 36 CPUs, wired into one liquid-cooled machine

$3,000,000
  • GPU memory13,824 GB
  • Power draw120,000 W
  • GPUs in unit72
rack cluster

NVIDIA GB300 NVL72

NVIDIA's largest rack-scale system, tuned for serving reasoning models at scale

$6,500,000
  • GPU memory20,736 GB
  • Power draw140,000 W
  • GPUs in unit72