Compute Comparison
vs
All comparisons →

CDNA 3

AMD Instinct MI300X

wins

4

The AMD MI300X leads all GPUs on memory capacity (192GB HBM3) and bandwidth (5.3 TB/s), making it exceptional for serving very large language models that don't fit on H100.

Memory-bound LLM inferenceLarge model servingHPC

Hopper

NVIDIA H200 141GB

wins

1

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

AMD Instinct MI300X

Metric

NVIDIA H200 141GB

FP16 TFLOPS

1.3k T
989 T

Bandwidth

5.3k GB/s
4.8k GB/s

VRAM

1.9k GB
1.4k GB

TDP (lower=better)

750 W
700 W

TFLOPS/watt

1.74
1.41

GB/s per watt

7.07
6.86

Full specification table

SpecAMD Instinct MI300XNVIDIA H200 141GB
ArchitectureCDNA 3Hopper
VRAM192 GB HBM3141 GB HBM3e
VRAM typeHBM3HBM3e
Memory bandwidth5,300 GB/s4,800 GB/s
FP16 TFLOPS1,307 TFLOPS989 TFLOPS
TDP750 W700 W
TFLOPS/watt1.74 T/W1.41 T/W
GB/s per watt7.07 GB/s/W6.86 GB/s/W
NVLinkNoYes
Release year20232024

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

AMD Instinct MI300X

FP16 TFLOPS1,307 TFLOPS
TDP750 W
TFLOPS/watt1.743 T/W
GB/s per watt7.07 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 AMD Instinct MI300X for:

  • Memory-bound LLM inference
  • Large model serving
  • HPC

Choose NVIDIA H200 141GB for:

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