PyyanThe AI Index

Pyyan / Compare / MI400 vs H100 vs TPU v7 Ironwood

MI400 vs H100 vs TPU v7 Ironwood

3 of 5

GPU & AI Chips · verified 13 Aug 2026

×MI400AMDcurrent
×H100NVIDIAcurrent
×TPU v7 IronwoodGooglecurrent
2 slots left
SpecificationMI400H100TPU v7 Ironwood
SummaryDouble NVIDIA's memory capacity.The workhorse of the previous generation.Inference-oriented, Google Cloud only.
Memory432GB HBM480GB HBM3192GB HBM3e
Bandwidth19.6 TB/s—7.37 TB/s
Price—$25–40K—
VendorAMDNVIDIAGoogle
CategoryGPU & AI ChipsGPU & AI ChipsGPU & AI Chips
OfficialAMD ↗NVIDIA ↗Google ↗

Highlighted rows are where these differ.

MI400

  • 19.6 TB/s bandwidth
  • 40 PFLOPS FP4
  • $7.2B in commitments

Best for large-model inference.

Full spec sheet →

H100

The workhorse of the previous generation.

Best for value.

Full spec sheet →

TPU v7 Ironwood

  • Requires JAX
  • Not purchasable or on any marketplace

Best for GCP inference.

Full spec sheet →