NVIDIA H100 SXM5 80GB

Hopper SXM 2022 4nm Spec confidence: Official
FP8 (dense)
1,979
TFLOPS
FP32
67
TFLOPS
VRAM
80 GB
Bandwidth
3.4 TB/s
memory
TDP
700 W
95.7 TFLOPS/kW

Performance

Peak theoretical throughput by precision type

INT8
8-bit integer
1,979 TOPS
3,958 with sparsity
FP8
8-bit floating point
1,979 TFLOPS
3,958 with sparsity
FP16
16-bit floating point
990 TFLOPS
1,979 with sparsity
BF16
Brain Float 16
990 TFLOPS
1,979 with sparsity
TF32
TensorFloat-32
494 TFLOPS
989 with sparsity
FP32
32-bit floating point
67 TFLOPS
FP64_TC
64-bit floating point with Tensor Cores
67 TFLOPS
FP64
64-bit floating point
34 TFLOPS
Dense Added with sparsity
2.827 TFLOPS/W FP8 at 700 W
1.414 TFLOPS/W FP16 at 700 W
0.096 TFLOPS/W FP32 at 700 W

The H100 SXM5 80GB in the GPU landscape

Peak FP16 TFLOPS (dense) against TDP, single-GPU parts tracked by Flopper

06001,2001,8002,4003,0000 W250 W500 W750 W1000 W1250 W1500 WInstinct MI355XH100 SXM5 80GB

Higher and further left is better: more half-precision throughput for less power.

Specifications

Architecture

Hopper

Form Factor

SXM

Launch Year

2022

Process Node

4nm

Memory

80 GB

Bandwidth

3,350 GB/s

TDP

700 W

Max Power

~805 W

Spec Confidence

Official

Full Specifications

Memory
VRAM 80 GB
Bandwidth 3.4 TB/s
Power & Thermal
TDP 700 W
Enterprise Features
Sparsity Yes
General
Form Factor SXM
Architecture Hopper
Launch Year 2022

Datasheet & Resources

Data Provenance

Every figure traced to a source

Primary Source

Publisher
NVIDIA
Published
2022-03-22

Data Quality

Spec confidence
Official
Clock basis
Boost
Precisions tracked
8
Normalization
All values in TFLOPS

Rent this GPU

$1.63 / GPU-hr

Lowest of 11 live listings across 9 providers· median $3.29

See all rental prices →

Price history and every provider on the pricing page. Some links are affiliate links.

Similar GPUs

NVIDIA H200 SXM 141GB

SXM · 2024
FP32: 67 TFLOPS
Compare vs H200

NVIDIA GH200 96GB HBM3

SXM · 2023
FP32: 67 TFLOPS
Compare vs GH200

NVIDIA GH200 144GB HBM3e

SXM · 2024
FP32: 67 TFLOPS
Compare vs GH200

NVIDIA H100 NVL 94GB

PCIe · 2023
FP32: 60 TFLOPS
Compare vs H100

NVIDIA H200 NVL 141GB

PCIe · 2024
FP32: 60 TFLOPS
Compare vs H200

Systems Using This GPU

Pre-configured systems featuring the NVIDIA H100

SystemGPU CountPeak PerformanceTotal Power
Supermicro GPU SuperServer AS -8125GS-TNHR (HGX H100)
GPU SuperServer · rack · 2024
8x H100 15.83 PFLOPS -- View System
NVIDIA DGX H100
DGX · rack · 2022
8x H100 15.83 PFLOPS 8.5 kW View System
NVIDIA HGX H100 4-GPU
HGX · baseboard · 2022
4x H100 7.92 PFLOPS 4.2 kW View System
NVIDIA HGX H100 8-GPU
HGX · baseboard · 2022
8x H100 15.83 PFLOPS 8.0 kW View System
Lenovo ThinkSystem SR780a V3 (HGX H100)
ThinkSystem · rack ·
8x H100 -- -- View System

Frequently Asked Questions

How many TFLOPS does the NVIDIA H100 have?

The NVIDIA H100 delivers 67 TFLOPS for FP32 operations, 990 TFLOPS for FP16, and 1979 TFLOPS for FP8 precision.

What is the power consumption of the NVIDIA H100?

The NVIDIA H100 has a TDP (Thermal Design Power) rating of 700 watts.

How much memory does the NVIDIA H100 have?

The NVIDIA H100 is equipped with 80 GB of VRAM with 3350 GB/s memory bandwidth.

What architecture is the NVIDIA H100 based on?

The NVIDIA H100 is based on the Hopper architecture, launched in 2022.

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