Supercomputers

The NVIDIA DGX Spark is a compact AI supercomputer powered by the NVIDIA GB10 Grace Blackwell Superchip. It delivers up to 1,000 AI TOPS (Tera Operations Per Second) of FP4 performance, making it suitable for tasks such as fine-tuning, inference, and prototyping of large AI models with up to 200 billion parameters. The system features 128 GB of unified LPDDR5x memory with a 256-bit interface and 273 GB/s memory bandwidth. Storage options include 1 TB or 4 TB NVMe M.2 SSDs with self-encryption

The NVIDIA DGX Station is a powerful AI workstation designed to bring data center-level AI performance to office environments. It features four NVIDIA Tesla V100 GPUs, each with 16GB of HBM2 memory, providing a total of 64GB of GPU memory. The system is powered by an Intel Xeon E5-2698 v4 processor with 20 cores, delivering exceptional computational capabilities. With 256GB of DDR4 system memory and a storage configuration of 3x 1.92TB SSDs in RAID 0 for data and 1x 1.92TB SSD for the operating system, the DGX Station ensures fast data access and processing.

The NVIDIA IGX Orin 700 is an industrial-grade edge AI platform designed for mission-critical applications in sectors such as healthcare, transportation, and industrial automation. It combines high-performance computing with advanced functional safety and security features. Powered by the NVIDIA Orin SoC, it integrates a 12-core Arm Cortex-A78AE CPU and a 2048-core NVIDIA Ampere architecture GPU with 64 Tensor Cores, delivering up to 1705 TOPS of AI performance. 

The NVIDIA IGX Orin 500 is an industrial-grade edge AI platform designed for mission-critical applications in sectors such as healthcare, transportation, and industrial automation. It combines high-performance computing with advanced functional safety and security features. Powered by the NVIDIA Orin SoC, it integrates a 12-core Arm Cortex-A78AE CPU and a 2048-core NVIDIA Ampere architecture GPU with 64 Tensor Cores, delivering up to 1705 TOPS of AI performance. 

The NVIDIA IGX Orin Developer Kit features a 12-core Arm Cortex-A78AE CPU and an integrated Ampere architecture GPU with 2,048 CUDA cores and 64 Tensor Cores, delivering up to 248 INT8 TOPS of AI performance. It includes 64 GB LPDDR5 memory with 204.8 GB/s bandwidth and a 500 GB NVMe SSD. The kit offers advanced networking with dual 100 GbE ports via ConnectX-7 and supports PCIe Gen5 expansion. It includes USB 3.2 Gen2, DisplayPort 1.4a, HDMI 2.0b, and integrated Wi-Fi/Bluetooth

The NVIDIA GB200 NVL72 is a rack-scale, liquid-cooled AI supercomputer that integrates 36 Grace CPUs and 72 Blackwell GPUs, interconnected via fifth-generation NVLink, delivering 130 TB/s of GPU communication bandwidth. It provides up to 1,440 PFLOPS of FP4 AI performance and supports up to 13.5 TB of HBM3e GPU memory with 576 TB/s bandwidth. 

The NVIDIA GB200 Grace Blackwell Superchip integrates two Blackwell B200 Tensor Core GPUs with a Grace CPU via a 900 GB/s NVLink-C2C interconnect. This configuration delivers up to 40 PFLOPS of FP4 AI performance, 20 PFLOPS of FP8/FP6, and 10 PFLOPS of FP16/BF16, with 384 GB of HBM3e GPU memory offering 16 TB/s bandwidth. The Grace CPU, featuring 72 Arm Neoverse V2 cores, supports up to 480 GB of LPDDR5X memory with 512 GB/s bandwidth. 

The NVIDIA GB300 NVL72 is a fully liquid-cooled, rack-scale AI supercomputer that integrates 72 NVIDIA Blackwell Ultra GPUs and 36 NVIDIA Grace CPUs. This configuration delivers up to 1,400 PFLOPS of FP4 AI performance, with 21 TB of HBM3e GPU memory providing 576 TB/s bandwidth.

The NVIDIA GH200 Grace Hopper Superchip integrates a 72-core Arm Neoverse V2 Grace CPU with an H100 Tensor Core GPU via a 900 GB/s NVLink-C2C interconnect. This configuration delivers up to 4 PFLOPS of AI performance, with 96 GB of HBM3 GPU memory offering 4 TB/s bandwidth and up to 480 GB of LPDDR5X CPU memory with 500 GB/s bandwidth. The GH200 Superchip is designed for large-scale AI and HPC applications, providing a unified memory architecture and enhanced energy efficiency.

The NVIDIA GH200 NVL2 Grace Hopper Superchip integrates two GH200 Superchips via NVLink, combining 144 Arm Neoverse V2 CPU cores and two Hopper GPUs. This configuration delivers up to 8 PFLOPS of AI performance, with 288 GB of HBM3e GPU memory offering 10 TB/s bandwidth and up to 960 GB of LPDDR5X CPU memory. The GH200 NVL2 is designed for compute- and memory-intensive workloads, providing 3.5× more GPU memory capacity and 3× more bandwidth than the NVIDIA H100 Tensor Core GPU in a single server.