NVIDIA GH200 Grace Hopper

The NVIDIA GH200 Grace Hopper is a Data Center graphics card based on the Hopper architecture. Released on 2023-05-29 with a launch price of $50,000.00, it features 14,592 CUDA cores and 138 GB of HBM3 memory.

GH200 Grace Hopper GPU

General info about GH200 Grace Hopper

Architecture Hopper (GH100)
Market Segment Data Center
Release Date 2023-05-29
Launch Price $50,000.00
Manufacturing Process 4nm

Technical specs of GH200 Grace Hopper

CUDA Cores 14,592
Base Clock Speed 1410 MHz
Boost Clock Speed 1830 MHz
Transistor Count 80B
VRAM Capacity 138 GB HBM3
Memory Bus Width 5120 bits
Memory Bandwidth 3000.0 GB/s
TDP 1000 W

Key Technical Parameters

Key technical parameters of the NVIDIA GH200 Grace Hopper include its 14,592 CUDA cores, 1410 MHz base clock, and 1830 MHz boost clock, delivering high performance for data center applications.

Benchmark performance of GH200 Grace Hopper

FP32 Performance

67

TFLOPS

FP16 Performance

2000

TFLOPS

The NVIDIA GH200 Grace Hopper achieves 67 TFLOPS in FP32 performance, making it ideal for data center workloads.

Gaming performance of GH200 Grace Hopper

Gaming Performance

The NVIDIA GH200 Grace Hopper is not designed for gaming. It is optimized for AI training, machine learning, and high-performance computing workloads.

Features and connectivity of GH200 Grace Hopper

Tensor Cores

Gen 4

Transformer Engine

Enabled

Flash Attention

Not Supported

Connectivity

NVLink 4, PCIe Gen5

Physical dimensions of GH200 Grace Hopper

Length 12in
Width 5in
Height 3-slot

Rankings and efficiency of GH200 Grace Hopper

Ranking Position #2
Popularity Ranking #8
Cost Effectiveness 0.7/5
Power Efficiency 1.4/5

Cloud Availability

Available Instances

0

Starting Price

$0.00/hr

Top GPUs for Training and Inference

Category Rank 1 Rank 2 Rank 3
Best for Training NVIDIA H200 NVIDIA H100 NVIDIA B200
Best for Inference NVIDIA A40 NVIDIA A100 NVIDIA A10

Compare GPU specifications and cloud instances to find the best GPU for your workload.