NVIDIA GH200 144GB HBM3e

Hopper SXM 2024 4nm
FP32
67.0
TFLOPS
VRAM
144 GB
HBM3e
TDP
1.0 kW
67.0 TFLOPS/kW
Bandwidth
4.9 TB/s
memory

Overview

The 144 GB HBM3e configuration of the NVIDIA GH200 Grace Hopper Superchip, and the one most cloud providers rent. It keeps the 72-core Grace CPU, the Hopper H100 GPU and the 900 GB/s NVLink-C2C link of the 96 GB part, and changes only the memory system: 144 GB of HBM3e at 4.9 TB/s in place of 96 GB of HBM3 at 4 TB/s. With up to 480 GB of LPDDR5X on the CPU side that gives 624 GB of fast-access memory in one coherent address space. Compute is unchanged, because NVIDIA publishes a single performance table for both configurations, so the 50 percent extra capacity and 23 percent extra bandwidth are the whole of the difference. That matters most where the working set rather than the arithmetic is the constraint, which is why this part shows up under long-context inference and large-embedding retrieval rather than under training benchmarks.

Performance Metrics

Peak theoretical throughput by precision type

PrecisionBitsPeak TFLOPSEfficiency
INT8 8 1979.0 1.979 TFLOPS/W
FP8 8 1979.0 1.979 TFLOPS/W
FP16 16 990.0 0.990 TFLOPS/W
BF16 16 990.0 0.990 TFLOPS/W
TF32 32 494.0 0.494 TFLOPS/W
FP32 32 67.0 0.067 TFLOPS/W
FP64 64 34.0 0.034 TFLOPS/W
FP8 Efficiency
1.979 TFLOPS/W
1979.0 TFLOPS / 1000W
FP16 Efficiency
0.990 TFLOPS/W
990.0 TFLOPS / 1000W
FP32 Efficiency
0.067 TFLOPS/W
67.0 TFLOPS / 1000W

Power Specifications

TDP

1.0 kW

Max Power

1.1 kW

Power Connector

PCIe 16-pin

Cooling

Liquid

Memory Specifications

Capacity

144 GB

Type

HBM3e

Bandwidth

4900 GB/s

Interface

--

Hardware & Design

Form Factor

SXM

Architecture

Hopper

Process Node

4nm

Launch Year

2024

Variant

144GB HBM3e

Market Segment

Data Center

Full Specifications

Memory
VRAM 144 GB
Memory Type HBM3e
Bandwidth 4.9 TB/s
Interconnect & I/O
GPU-to-GPU NVLink-C2C
Interconnect Bandwidth 900 GB/s
Power & Thermal
TDP 1.0 kW
General
Form Factor SXM
Architecture Hopper
Launch Year 2024

Documentation & Resources

Common Use Cases

LLM Training LLM Inference Scientific Computing HPC Workloads

The NVIDIA GH200 is optimized for high-performance computing tasks with Hopper architecture delivering 67 TFLOPS of compute power.

Where to Rent

Compare cloud providers offering on-demand GPU instances for AI training, inference, and HPC workloads.

Browse GPU Cloud Providers

Similar GPUs

NVIDIA H100 SXM5 80GB

SXM · 2022
FP32: 67.0 TFLOPS
Compare vs H100

NVIDIA H200 SXM 141GB

SXM · 2024
FP32: 67.0 TFLOPS
Compare vs H200

NVIDIA GH200 96GB HBM3

SXM · 2023
FP32: 67.0 TFLOPS
Compare vs GH200

NVIDIA H100 NVL 94GB

PCIe · 2023
FP32: 60.0 TFLOPS
Compare vs H100

NVIDIA H200 NVL 141GB

PCIe · 2024
FP32: 60.0 TFLOPS
Compare vs H200

Stay Updated on GPU Releases

Get notified when new GPUs are added or specifications are updated.

Loading verification...

No spam, unsubscribe anytime.

Back to GPUs