Compute Comparison
vs
All comparisons →

Ampere

NVIDIA A100 80GB

wins

1

The A100 remains one of the most widely available data center GPUs. Its broad provider support and mature software ecosystem make it a reliable choice for ML training and inference.

ML trainingInference at scaleHPC

Hopper

NVIDIA H200 SXM 141GB

wins

4

The H200 SXM is the SXM5 form factor of the H200, with 141 GB HBM3e and 4.8 TB/s bandwidth.

Very large LLMsMemory-bound inferenceMulti-modal models

Performance comparison

Visual bars — winner highlighted

NVIDIA A100 80GB

Metric

NVIDIA H200 SXM 141GB

FP16 Tensor TFLOPS (dense)

312 T
989 T

Bandwidth

2.0k GB/s
4.8k GB/s

VRAM

80 GB
141 GB

TDP (lower=better)

400 W
700 W

TFLOPS/watt

0.78
1.41

GB/s per watt

5.10
6.86

Full specification table

SpecNVIDIA A100 80GBNVIDIA H200 SXM 141GB
ArchitectureAmpereHopper
VRAM80 GB HBM2e141 GB HBM3e
VRAM typeHBM2eHBM3e
Memory bandwidth2,039 GB/s4,800 GB/s
FP16 Tensor TFLOPS (dense)312 TFLOPS989 TFLOPS
TDP400 W700 W
TFLOPS/watt0.78 T/W1.41 T/W
GB/s per watt5.10 GB/s/W6.86 GB/s/W
NVLinkYesYes
Release year20202024

Live cloud pricing

On-demand pricing across providers — updated in real time

Per hourPer GB VRAM/hr

NVIDIA A100 80GB

Paperspace
$10.90/hr
IBM Cloud
$2.10/hr
Alibaba Cloud
$2.20/hr
Cloudzy
$1.49/hr
Replicate
$1.40/hr
Canopy Wave
$1.59/hr
TheAI Cloud
$0.99/hr
HIGHRESO
$398.00/hr

NVIDIA H200 SXM 141GB

No live pricing data available.

Salad: Lowest priority tier — preemptible

Power efficiency analysis

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

NVIDIA A100 80GB

FP16 TFLOPS312 TFLOPS
TDP400 W
TFLOPS/watt0.780 T/W
GB/s per watt5.10 GB/s/W

NVIDIA H200 SXM 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.

Performance-per-dollar

TFLOPS/$ and GB/s/$ at current best cloud prices

NVIDIA A100 80GB

Best cloud price$0.48/hr
TFLOPS per $650.0 T/$
GB/s per $4248 GB/s/$

NVIDIA H200 SXM 141GB

Best cloud priceN/A
TFLOPS per $—
GB/s per $—

TFLOPS/$ = FP16 TFLOPS ÷ best on-demand $/hr. Higher is better — more compute per dollar. GB/s/$ = memory bandwidth ÷ best on-demand $/hr. For memory-bound inference workloads (most LLM serving), GB/s/$ is often a better predictor of cost-efficiency than TFLOPS/$. Prices are live from the Compute Comparison API and update in real time.

Workload Cost Comparison

Total job cost = best on-demand $/hr × GPU count × hours

WorkloadScaleNVIDIA A100 80GBNVIDIA H200 SXM 141GB
7B LLM fine-tune8× GPU, 24 h$92—
70B LLM fine-tune64× GPU, 72 h$2.2k—
Inference server1× GPU, 730 h$350—
Image gen batch4× GPU, 8 h$15—

Based on current best on-demand prices. Spot pricing typically 40–70% lower. Actual cost depends on provider, region, and availability.

When to choose each GPU

Choose NVIDIA A100 80GB for:

  • ML training
  • Inference at scale
  • HPC

Weaknesses / Limitations

  • Older Ampere architecture — lower FP16 TFLOPS than H100 at similar price
  • No Ada Lovelace efficiency improvements
  • Being phased out by H100 on many platforms

Choose NVIDIA H200 SXM 141GB for:

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

Weaknesses / Limitations

  • Very limited cloud availability — fewer providers than H100
  • Premium pricing over H100 with same FP16 TFLOPS
  • 700 W TDP — same power envelope as H100 with no efficiency gain