Compute Comparison
vs
All comparisons →

Hopper

NVIDIA H100 80GB

wins

0

The NVIDIA H100 is the gold standard for AI training and inference. With 80GB HBM3 memory and NVLink 4.0 support, it dominates large-model training and multi-GPU clusters.

LLM trainingLarge-scale inferenceHPC workloads

Hopper

NVIDIA H200 141GB

wins

2

The H200 upgrades the H100 with 141GB HBM3e memory and 4.8 TB/s bandwidth — a massive boost for memory-bound workloads like large LLM inference.

Very large LLMsMemory-bound inferenceMulti-modal models

Performance comparison

Visual bars — winner highlighted

NVIDIA H100 80GB

Metric

NVIDIA H200 141GB

FP16 TFLOPS

989 T
989 T

Bandwidth

3.4k GB/s
4.8k GB/s

VRAM

803 GB
1.4k GB

TDP (lower=better)

700 W
700 W

TFLOPS/watt

1.41
1.41

GB/s per watt

4.79
6.86

Full specification table

SpecNVIDIA H100 80GBNVIDIA H200 141GB
ArchitectureHopperHopper
VRAM80 GB HBM3141 GB HBM3e
VRAM typeHBM3HBM3e
Memory bandwidth3,350 GB/s4,800 GB/s
FP16 TFLOPS989 TFLOPS989 TFLOPS
TDP700 W700 W
TFLOPS/watt1.41 T/W1.41 T/W
GB/s per watt4.79 GB/s/W6.86 GB/s/W
NVLinkYesYes
Release year20222024

Live cloud pricing

On-demand $/hr across providers — updated in real time

Loading prices…

Power efficiency analysis

TFLOPS/watt and GB/s/watt — critical for data center TCO

NVIDIA H100 80GB

FP16 TFLOPS989 TFLOPS
TDP700 W
TFLOPS/watt1.413 T/W
GB/s per watt4.79 GB/s/W

NVIDIA H200 141GB

FP16 TFLOPS989 TFLOPS
TDP700 W
TFLOPS/watt1.413 T/W
GB/s per watt6.86 GB/s/W

TFLOPS/watt measures compute efficiency — how much AI throughput you get per watt of power consumed. For data centers with PUE of 1.2–1.5, a 10% improvement in TFLOPS/watt translates directly to lower electricity costs and cooling requirements. GB/s/watt measures memory bandwidth efficiency, which is the binding constraint for memory-bound LLM inference workloads.

When to choose each GPU

Choose NVIDIA H100 80GB for:

  • LLM training
  • Large-scale inference
  • HPC workloads

Choose NVIDIA H200 141GB for:

  • Very large LLMs
  • Memory-bound inference
  • Multi-modal models