NVIDIA H200 NVL Tensor Core Graphics Card, 141GB Memory, 4.8 TB/s Memory Bandwidth, 7 NVDEC & 7 JPEG Decoders, Up to 3,341 TFLOPS, PCIe, Dual-Slot Air-Cooled Form Factor |

Description

NVIDIA H200 Tensor Core GPU

The GPU for Generative AI and HPC
The NVIDIA H200 Tensor Core GPU supercharges generative AI and high-performance computing (HPC) workloads with game-changing performance and memory capabilities. As the first GPU with HBM3e, the H200’s larger and faster memory fuels the acceleration of generative AI and large language models (LLMs) while advancing scientific computing for HPC workloads.

Specifications

FP64

30 TFLOPS

FP64 Tensor Core

60 TFLOPS

FP32

60 TFLOPS

TF32 Tensor Core²

835 TFLOPS

BFLOAT16 Tensor Core²

1,671 TFLOPS

FP16 Tensor Core²

1,671 TFLOPS

FP8 Tensor Core²

3,341 TFLOPS

INT8 Tensor Core²

3,341 TFLOPS

GPU Memory

141GB

GPU Memory Bandwidth

4.8 TB/s

Decoders

7 NVDEC, 7 JPEG

Confidential Computing

Supported

Max TDP

Up to 600W (configurable)

Multi-Instance GPUs (MIG)

Up to 7 MIGs @16.5GB each

Form Factor

PCIe, Dual-slot air-cooled

Interconnect

NVLink Bridge: 900GB/s/GPU
PCIe Gen5: 128GB/s

Server Options

NVIDIA MGX H200 NVL systems (up to 8 GPUs)

NVIDIA AI Enterprise

Included