NVIDIA H200 SXM 141GB

Hopper SXM 2024 4nm
FP32
67.0
TFLOPS
VRAM
141 GB
TDP
700 W
95.7 TFLOPS/kW
Bandwidth
4.8 TB/s
memory

Performance Metrics

Peak theoretical throughput by precision type

PrecisionPeak TFLOPSEfficiency
INT8 1979.0 2.827 TFLOPS/W
FP8 1979.0 2.827 TFLOPS/W
FP16 989.5 1.414 TFLOPS/W
BF16 989.5 1.414 TFLOPS/W
TF32 494.5 0.706 TFLOPS/W
FP32 67.0 0.096 TFLOPS/W
FP64 34.0 0.049 TFLOPS/W
FP8 Efficiency
2.827 TFLOPS/W
1979.0 TFLOPS / 700W
FP16 Efficiency
1.414 TFLOPS/W
989.5 TFLOPS / 700W
FP32 Efficiency
0.096 TFLOPS/W
67.0 TFLOPS / 700W

Power Specifications

TDP

700 W

Max Power

805 W

Power Connector

PCIe 16-pin

Cooling

Liquid

Memory Specifications

Capacity

141 GB

Type

--

Bandwidth

4800 GB/s

Interface

--

Hardware & Design

Form Factor

SXM

Architecture

Hopper

Process Node

4nm

Launch Year

2024

Variant

SXM 141GB

Market Segment

Data Center

Documentation & Resources

Common Use Cases

LLM Training LLM Inference Scientific Computing HPC Workloads

The NVIDIA H200 is optimized for high-performance computing tasks with Hopper architecture delivering 67 TFLOPS of compute power.

Where to Rent

ProviderPrice/hr
RunPod
$3.59 View →
DataCrunch
$4.00 View →
Oracle Cloud (OCI)
$10.00 View →

Prices shown are approximate. Click through for current pricing.

Similar GPUs

NVIDIA H100 SXM5 80GB

SXM · 2022
FP32: 67.0 TFLOPS
Compare vs H100

NVIDIA GH200

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

NVIDIA H100 PCIe 80GB

PCIe · 2022
FP32: 51.0 TFLOPS
Compare vs H100

Systems Using This GPU

Pre-configured systems featuring the NVIDIA H200

SystemPeak Performance
NVIDIA DGX H200
DGX · rack · 2024
15.83 PFLOPS
NVIDIA HGX H200
HGX · baseboard · 2024
15.83 PFLOPS

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