-
NVIDIA
NVIDIA DGX Spark - GB10 Grace Blackwell Superchip, 128 GB Unified Memory, 1 PFLOP FP4, 4 TB NVMe Desktop AI SupercomputerNVIDIA DGX Spark is a compact desktop AI supercomputer built on the GB10 Grace Blackwell Superchip - up to a petaFLOP of FP4 AI performance with 128 GB of unified memory for prototyping, fine-tuning...- 24/7 Support
-
NVIDIA
NVIDIA DGX Station - GB300 Grace Blackwell Ultra Desktop Superchip, 784 GB Coherent Memory, ConnectX-8 SuperNICNVIDIA DGX Station brings data-centre-class Grace Blackwell Ultra performance to the desk: a GB300 Desktop Superchip with up to 784 GB of coherent memory for developing and running large AI models...- 24/7 Support
-
NVIDIA
NVIDIA DGX GB200 NVL72 Rack-Scale AI System - 36x Grace CPUs, 72x Blackwell GPUs, 13.5 TB HBM3e, Liquid CooledNVIDIA DGX GB200 NVL72 connects 36 Grace CPUs and 72 Blackwell GPUs in one liquid-cooled rack that operates as a single 72-GPU NVLink domain - the building block of DGX SuperPOD with DGX GB200...- 24/7 Support
-
NVIDIA
NVIDIA DGX H200 AI System - 8x H200 SXM GPUs, 1,128 GB GPU Memory, 32 PFLOPS FP8, 8UNVIDIA DGX H200 delivers eight H200 Tensor Core GPUs with 1,128 GB of aggregate GPU memory for large-model training and inference, with the DGX software stack and NVIDIA AI Enterprise.DGX systems are...- 24/7 Support
-
NVIDIA
NVIDIA DGX B200 AI System - 8x Blackwell GPUs, 1.4 TB HBM3e, 72 PFLOPS FP8 Training, 10UNVIDIA DGX B200 is a unified AI platform for training, fine-tuning and inference: eight Blackwell GPUs with 1.4 TB of HBM3e and fifth-generation NVLink, the building block of DGX SuperPOD.DGX systems...- 24/7 Support
-
NVIDIA
NVIDIA DGX B300 AI System - 8x Blackwell Ultra GPUs, 2.1 TB GPU Memory, 144 PFLOPS FP4, 10UNVIDIA DGX B300 is the eighth-generation DGX AI system: eight Blackwell Ultra GPUs with 2.1 TB of GPU memory delivering 144 petaFLOPS of FP4 inference, fully networked with 800 Gb/s ConnectX-8...- 24/7 Support
-