NVIDIA H200 NVL
About
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.
Specification
H200 NVL
FP64
34 TFLOPS
FP64 Tensor Core
67 TFLOPS
FP32
67 TFLOPS
TF32 Tensor Core
989 TFLOPS2²
BFLOAT16 Tensor Core
1,979 TFLOPS²
FP16 Tensor Core
1,979 TFLOPS²
FP8 Tensor Core
3,958 TFLOPS²
INT8 Tensor Core
3,958 TFLOPS²
GPU memory
141GB
GPU memory bandwidth
4.8TB/s
Decoders
7 NVDEC
7 JPEG
Confidential Computing
Supported
Max thermal design power (TDP)
Up to 600W (configurable)
Multi-Instance GPUs
Up to 7 MIGs @16.5GB each
Form factor
PCIe
Interconnect
2- or 4-way NVIDIA NVLink bridge: 900GB/s PCIe Gen5: 128GB/s
Server options
NVIDIA MGX™ H200 NVL partner and NVIDIA-Certified Systems with up to 8 GPUs
NVIDIA AI Enterprise
Included
You May Also Like
Related products
-

NVIDIA RTX A2000
SKU: 900-5G192-2551-000More Information- 6 GB | 12 GB GDDR6 with error-correction code (ECC)
- 4x mini DisplayPort 1.4
- PCI Express Gen 4 x 16
-

NVIDIA RTX A5000
SKU: 900-5G132-2500-000More Information- GPU Memory: 24GB GDDR6 with error-correcting code (ECC)
- 4x DisplayPort 1.4
- PCI Express Gen 4 x 16
-

NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
SKU: N/AKey Features > Enhanced Streaming Multiprocessors (SMs) built for neural shaders > 5th Gen Tensor Cores support FP4 precision, DLSS 4 Multi Frame Generation > 4th Gen Ray Tracing Cores built for detailed geometry > 96 GB of GDDR7 memory > 1.8 TB/s of memory bandwidth > 9th Gen NVENC and 6th Gen NVDEC with 4:2:2 support > PCIe Gen 5 > Four Display Port 2.1b connectors > Multi-instance GPU (MIG) support > AI Management ProcessorMore Information
Our Customers





























Previous
Next
