DGX Station takes advantage of Nvidia's latest GB300 Grace Blackwell Ultra Desktop Superchip that combines a 72-core Grace CPU with a Blackwell Ultra GPU linked together with a 900 GB/s NVLink C2C interface. The system comes armed with a whopping 748GB of total onboard memory; the CPU portion is paired to 496GB of LPDDR5X rated at 396GB/s of bandwidth, and the GPU is paired with 252GB of HBM3e memory rated at 7.1 TB/s of bandwidth. Both memory pools are unified, allowing the CPU and GPU to share each other's memory for maximum AI performance.
Just like a typical workstation PC, Nvidia has armed the DGX Station with three PCIe Gen 5 x16 slots, one wired with 16 lanes and eight lanes for the other two. The workstation system officially supports discrete GPU options to plug into its PCIe slots for extra tasks such as simulation and ray-traced visualization.
You may like Nvidia DGX Spark review: the GB10 Superchip powers a fast and fun AI toolbox that beats out AMD’s Ryzen AI Max+ 395 Nvidia DGX Spark gets 18% price increase as memory shortages bite Nvidia DGX Spark update cuts idle power by 32% or more Supported GPUs are the RTX Pro 6000 Workstation Edition, RTX Pro 6000 Blackwell Max-Q Workstation Edition, RTX Pro 4000 Blackwell SFF Edition, and RTX Pro 2000 Blackwell graphics cards. There are also four M.2 slots, audio connectors, and USB ports.
The workstation uses Nvidia's ConnectX-8 SuperNIC for networking, which supports speeds of up to 800 Gb/s through two QSFP112 ports. The system is designed to accelerate AI projects by hooking up to two DGX Stations together to scale model capacity and performance. Power connectivity comes in the form of a single 24-pin ATX power connector, a single 8-pin EPS connector, and three 12V-2×6 power connectors for the GPU, to feed the system's 1600W official power rating.
Follow Tom's Hardware on Google News , or add us as a preferred source , to get our latest news, analysis, & reviews in your feeds.
Get Tom's Hardware's best news and in-depth reviews, straight to your inbox.
Key considerations
- Investor positioning can change fast
- Volatility remains possible near catalysts
- Macro rates and liquidity can dominate flows
Reference reading
- https://www.tomshardware.com/tech-industry/artificial-intelligence/SPONSORED_LINK_URL
- https://www.tomshardware.com/tech-industry/artificial-intelligence/nvidia-launches-dgx-station-with-its-bleeding-edge-gb300-grace-blackwell-superchip-now-available-to-order-and-will-begin-shipping-in-the-coming-months#main
- https://www.tomshardware.com/subscription
- Score a liquid-cooled Asus ROG 4K gaming PC with a 9800X3D and RX 9070 XT for under $1,900 right now — powerhouse rig comes equipped with 32GB of DDR5 RAM and a
- Bitcoin is so resilient it could survive as much as 90% of the world's undersea cables failing simultaneously — study reveals Bitcoin could still be very vulner
- Nvidia launches DGX Station with its bleeding-edge GB300 Grace Blackwell Superchip — now available to order and will begin shipping in the coming months
- Nvidia removes Rubin CPX accelerators from its roadmap — Groq 3 LPUs take center stage as CPX is removed
- With H200s set to flow into China, Groq is reportedly set to follow — Nvidia is allegedly preparing a custom version of inferencing chip to penetrate region
Informational only. No financial advice. Do your own research.