NVIDIA offers DGX
Product
Purpose-built AI supercomputers integrating GPUs, CPUs, networking, and software for enterprise training and inference.
- Currently Offered
DGX is NVIDIA's family of purpose-built artificial intelligence supercomputers that integrate Blackwell or Hopper GPUs, Grace CPUs, NVLink, NVSwitch, BlueField data processing units, and Quantum InfiniBand networking into rack-scale systems for training, inference, and data analytics.
The DGX platform spans single-node DGX B200 systems, the rack-scale DGX GB200 NVL72, and the DGX SuperPOD reference architecture for multi-rack data center deployments. NVIDIA ships DGX with the NVIDIA AI Enterprise software stack, Mission Control orchestration, and Base Command management.
Purpose-built AI supercomputers integrating GPUs, CPUs, networking, and software for enterprise training and inference.
Supermicro server systems powered by NVIDIA RTX PRO Blackwell Server Edition GPUs for enterprise AI, HPC, and visual computing.
The HP ZGX Nano AI Station is a compact desktop AI development system from HP.
Dell Pro Max with GB10 is Dell's compact desktop AI development system built on the NVIDIA GB10 superchip.
The ASUS Ascent GX10 is a compact desktop AI supercomputer built on the NVIDIA GB10 superchip.
HPE Cray XD670 is a 5U AI training server supporting eight NVIDIA H100 or H200 SXM5 GPUs.
Dedicated physical GPU servers without virtualization overhead for maximum AI performance.
Arista AI Networking is a portfolio for high-performance AI cluster connectivity.
Lenovo ThinkSystem SR675 V3 is a GPU-optimized rack server for enterprise artificial intelligence and professional graphics workloads.
Supermicro server systems powered by NVIDIA RTX PRO Blackwell Server Edition GPUs for enterprise AI, HPC, and visual computing.
The HP ZGX Nano AI Station is a compact desktop AI development system from HP.
Dell Pro Max with GB10 is Dell's compact desktop AI development system built on the NVIDIA GB10 superchip.
The ASUS Ascent GX10 is a compact desktop AI supercomputer built on the NVIDIA GB10 superchip.
HPE Cray XD670 is a 5U AI training server supporting eight NVIDIA H100 or H200 SXM5 GPUs.
Cray XD670 is an HPE GPU-dense server for AI training and HPC.
Dedicated physical GPU servers without virtualization overhead for maximum AI performance.
Arista AI Networking is a portfolio for high-performance AI cluster connectivity.
Lenovo ThinkSystem SR675 V3 is a GPU-optimized rack server for enterprise artificial intelligence and professional graphics workloads.
