NVIDIA DGX Station
NVIDIA DGX Station is a desktop AI supercomputer powered by the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip with massive unified memory and NVLink-C2C high-bandwidth interconnect. Built for AI developers, researchers, and data scientists, it delivers data-center-class performance for large-scale model training, inference, and AI workloads right from a workstation. DGX Station comes with the NVIDIA AI software stack, including DGX OS and support for NVIDIA AI Enterprise, enabling seamless development and deployment from desktop to cloud or enterprise infrastructure.
Desktop AI Supercomputer for the Era of Generative AI
The NVIDIA DGX Station brings data-center-class AI performance to the desktop. Powered by the NVIDIA GB300 Grace Blackwell Ultra Superchip, DGX Station enables AI developers, researchers, and data scientists to build, train, and deploy advanced AI models locally with massive unified memory and exceptional compute performance.
Unified Grace Blackwell Architecture
DGX Station integrates an NVIDIA Grace CPU and NVIDIA Blackwell Ultra GPU through ultra-high-bandwidth NVLink-C2C, delivering a unified CPU–GPU memory architecture. With up to 784 GB of coherent system memory, DGX Station is purpose-built for large language models, multimodal AI, and complex data science workloads.
Enterprise-Grade Performance in a Workstation Form Factor
Designed for professional environments, DGX Station delivers unprecedented AI performance in a compact workstation design. Advanced cooling and power efficiency enable sustained performance for long-running AI training and inference workloads, while high-speed networking allows seamless scaling across multiple DGX systems or cloud environments.
Key Features
- Powered by NVIDIA GB300 Grace Blackwell Ultra Superchip
- Up to 784 GB unified CPU–GPU coherent memory
- NVIDIA Blackwell Ultra GPU with HBM3e memory
- NVLink-C2C interconnect for ultra-high bandwidth CPU–GPU communication
- Support for NVIDIA Multi-Instance GPU (MIG)
- Integrated NVIDIA ConnectX-8 SuperNIC for high-speed networking
- Runs NVIDIA DGX OS and supports NVIDIA AI Enterprise software
- Desktop AI supercomputer for enterprise and research workloads
| MFG Number | NVIDIA-DGX-STATION-GB300 |
|---|---|
| Condition | Item Condition : Brand New |
| Price | $300,000.00 |
| Show Product Will Be Available Soon on FE | No |
| Financing | Yes |
| Product Card Description | The NVIDIA GB200 NVL72 is a liquid-cooled, data-centre-class AI server delivering unprecedented performance for generative AI, large language models and HPC workloads. With a 72-GPU NVLink domain, the system acts as a unified accelerator delivering up to 1,440 PFLOPS FP4, 720 PFLOPS FP8, and supports massive 13.4 TB HBM3e memory and 130 TB/s high-speed interconnect. Designed for real-time trillion-parameter inference (30× H100) and large-scale training (4× H100), this rack-scale solution enables hyperscale AI infrastructure with extreme throughput and efficiency. |
| Order Processing Guidelines | Order Processing Guidelines:
Inquiry First – Please reach out to our team to discuss your requirements before placing an order. |
