Compute Comparison
vs
All comparisons →

Hopper

NVIDIA H200 SXM 141GB

wins

3

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

Ada Lovelace

NVIDIA L4

wins

2

The NVIDIA L4 is the most power-efficient Ada Lovelace GPU at just 72W TDP. It delivers 121 TFLOPS FP16 (dense) and 242.5 TFLOPS FP8 (dense).

Efficient inferenceVideo transcodingEdge AI

Performance comparison

Visual bars — winner highlighted

NVIDIA H200 SXM 141GB

Metric

NVIDIA L4

FP16 Tensor TFLOPS (dense)

989 T
121 T

Bandwidth

4.8k GB/s
300 GB/s

VRAM

141 GB
24 GB

TDP (lower=better)

700 W
72 W

TFLOPS/watt

1.41
1.68

GB/s per watt

6.86
4.17

Full specification table

SpecNVIDIA H200 SXM 141GBNVIDIA L4
ArchitectureHopperAda Lovelace
VRAM141 GB HBM3e24 GB GDDR6
VRAM typeHBM3eGDDR6
Memory bandwidth4,800 GB/s300 GB/s
FP16 Tensor TFLOPS (dense)989 TFLOPS121 TFLOPS
TDP700 W72 W
TFLOPS/watt1.41 T/W1.68 T/W
GB/s per watt6.86 GB/s/W4.17 GB/s/W
NVLinkYesNo
Release year20242023

Live cloud pricing

On-demand pricing across providers — updated in real time

Per hourPer GB VRAM/hr
Loading prices…

Power efficiency analysis

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

NVIDIA H200 SXM 141GB

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

NVIDIA L4

FP16 TFLOPS121 TFLOPS
TDP72 W
TFLOPS/watt1.681 T/W
GB/s per watt4.17 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 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

Choose NVIDIA L4 for:

  • Efficient inference
  • Video transcoding
  • Edge AI

Weaknesses / Limitations

  • 24 GB VRAM limits model size — cannot run 34B+ models
  • Low memory bandwidth (300 GB/s) — bottleneck for throughput-sensitive inference
  • Not suitable for training or fine-tuning beyond small models