H100 CNX — Full Specifications

nvidia Hopper · FP32: 53.84 TFLOPS · Memory: 80.0 GB HBM2e · TDP: 350.0W

Last updated:

Calculated from published specifications — a Quanteta index, not measured FPS / benchmark results.

Quanteta Performance Indices

QOV ? Overall Performance Index 23.6 / 100 top 2%
QAI ? Compute (AI) Strength 19.6 / 100 top 2%
QGP ? Graphics Index 41.6 / 100 top 2%
QWP ? Power Efficiency Index 25.9 / 100 top 7%
QME ? Memory Bandwidth Density 0.2 / 100 top 69%

Methodology

Full Specifications

GPU ID
nvidia-h100-cnx
Vendor
nvidia
Manufacturer
NVIDIA
GPU Chip
GH100
Architecture
Hopper
Generation
Server Hopper(Hxx)
Process
5.0nm
Transistors
80.0B
Die Size
814.0 mm²
Release
2023-03-21
Bus Interface
PCIe 5.0 x16
Base Clock
690.0 MHz
Boost Clock
1845.0 MHz
Memory
80.0 GB HBM2e
Memory Bus
5120.0-bit
Bandwidth
2040.0 GB/s
Shaders
14592.0
TMUs
456.0
ROPs
24.0
Tensor Cores
456.0
TDP
350.0W
FP32
53.84 TFLOPS
FP16
215.40 TFLOPS
FP64
26.92 TFLOPS
Source
TechPowerUp
Check price on Amazon

Search link to Amazon.co.jp. We do not collect price or stock data — Amazon shows the current price and availability. As an Amazon Associate, Quanteta earns from qualifying purchases.

Related GPUs

GPUs with the closest value on each axis. A descriptive neighbourhood derived from the calculated indices — not a recommendation.

Closest Overall Performance Index

RTX 5000 Mobile Ada Generation 23.4 QOV 23.4 / 100 Radeon PRO W7900D 23.3 QOV 23.3 / 100 Radeon RX 7900 XT 23.1 QOV 23.1 / 100

Closest Compute (AI) Strength

H800 PCIe 80 GB 18.7 QAI 18.7 / 100 H100 PCIe 80 GB 18.7 QAI 18.7 / 100 H800 SXM5 22.2 QAI 22.2 / 100

Closest Graphics Index

Radeon RX 7900 GRE 41.6 QGP 41.6 / 100 GeForce RTX 4080 41.5 QGP 41.5 / 100 Radeon PRO W7800 48 GB 41.0 QGP 41.0 / 100

Closest Memory Bandwidth

A800 SXM4 80 GB 2040 GB/s QME 0.2 / 100 A100X 2040 GB/s QME 0.2 / 100 A100 SXM4 80 GB 2040 GB/s QME 0.2 / 100
Compare · ← Back to all GPUs