AI & HPC Infrastructure

NVIDIA ConnectX-8 C8240 400G HHHL SuperNIC | 900-9X81Q-00CN-ST0

NVIDIA ConnectX-8 C8240 HHHL dual-port QSFP112 SuperNIC with 400GbE or NDR 400Gb/s InfiniBand, PCIe Gen6 x16, and SocketDirect for production AI and HPC servers.

NVIDIA ConnectX-8 C8220 200G HHHL SuperNIC | 900-9X81Q-00CV-ST0

NVIDIA ConnectX-8 C8220 HHHL dual-port QSFP112 SuperNIC with 200GbE or 200Gb/s InfiniBand and PCIe Gen5 x16.

NVIDIA ConnectX-8 C8180P OCP 3.0 800G SuperNIC | 900-9X85E-00EX-MJ0

NVIDIA ConnectX-8 C8180P OCP 3.0 TSFF SuperNIC with PCIe Gen6 x16, single OSFP, XDR 800Gb/s InfiniBand or 2x400GbE, offered in air- and partner-cooled prototype variants.

NVIDIA 900-9X81E-00EX-ST0 | ConnectX-8 C8180 / C8180L 800G HHHL SuperNIC

NVIDIA ConnectX-8 C8180/C8180L HHHL SuperNIC with PCIe Gen6 x16, single OSFP, XDR 800Gb/s InfiniBand or 2x400GbE.

NVIDIA BlueField-3 B3220 DPU | 900-9D3B6-00CV-AA0

NVIDIA BlueField-3 B3220 16-core DPU with 32 GB DDR5, PCIe Gen5 x16, dual QSFP112 ports, and 200GbE / NDR200 200Gb/s InfiniBand.

NVIDIA BlueField-3 B3210E DPU | 900-9D3B6-00CC-EA0

NVIDIA BlueField-3 B3210E 16-core DPU with 32 GB DDR5, PCIe Gen5 x16, dual QSFP112 ports, and 100GbE / HDR100 100Gb/s InfiniBand.

NVIDIA GB300 NVL72 Blackwell Ultra Rack-Scale AI Platform | GB300-NVL72

NVIDIA GB300 NVL72 fully liquid-cooled platform with 72 Blackwell Ultra GPUs, 36 Grace CPUs, 20 TB GPU memory, and 130 TB/s NVLink for AI reasoning and inference.

NVIDIA GB200-NVL72 | Grace Blackwell Rack-Scale AI Platform

NVIDIA GB200 NVL72 liquid-cooled rack-scale platform with 72 Blackwell GPUs, 36 Grace CPUs, 13.4 TB HBM3e, and a 130 TB/s NVLink domain.

NVIDIA DGX GB300 NVL72 | Rack-Scale Blackwell Ultra AI System

NVIDIA DGX GB300 NVL72 rack-scale Blackwell Ultra system with 72 GPUs, 36 Grace CPUs, about 20 TB GPU memory, NVLink, and DGX software.

NVIDIA DGX GB200 NVL72 | Rack-Scale AI System | DGX-GB200-NVL72

NVIDIA DGX GB200 NVL72 rack-scale Grace Blackwell system with 72 Blackwell GPUs, 36 Grace CPUs, 13.4 TB HBM3e, NVLink, and NVIDIA DGX system software.

NVIDIA GB200 NVL4 | Grace Blackwell HPC and AI Platform

NVIDIA GB200 NVL4 liquid-cooled MGX platform with 4 Blackwell GPUs and 2 Grace CPUs over NVLink-C2C for scientific computing, AI for science, training, and inference.

NVIDIA HGX B300 8-GPU AI Platform | HGX-B300

NVIDIA HGX B300 eight-GPU platform with 2.1 TB HBM3e, fifth-generation NVLink, and 1.6 TB/s platform networking for OEM AI servers.

NVIDIA HGX B200 8-GPU AI Platform | HGX-B200

NVIDIA HGX B200 eight-GPU platform with 1.4 TB HBM3e, fifth-generation NVLink, and 0.8 TB/s platform networking for AI servers.

NVIDIA DGX B300 8-GPU Blackwell Ultra AI System | DGX-B300

NVIDIA DGX B300 10U Blackwell Ultra system with 8 B300 GPUs, 2.1 TB HBM3e, ConnectX-8 800G networking, BlueField-3 DPUs, and flexible AC or DC data center power options.

NVIDIA DGX B200 8-GPU Blackwell AI System | DGX-B200

NVIDIA DGX B200 10U AI system with 8 Blackwell GPUs, 1.44 TB HBM3e, NVLink, dual Xeon CPUs, ConnectX-7 networking, and BlueField-3 DPUs for training and inference.