PyyanThe AI Index

Pyyan / Compare / TPU v7 Ironwood vs MI400 vs H100

TPU v7 Ironwood vs MI400 vs H100

3 of 5

GPU & AI Chips · verified 13 Aug 2026

×TPU v7 IronwoodGooglecurrent
×MI400AMDcurrent
×H100NVIDIAcurrent
2 slots left
SpecificationTPU v7 IronwoodMI400H100
SummaryInference-oriented, Google Cloud only.Double NVIDIA's memory capacity.The workhorse of the previous generation.
Memory192GB HBM3e432GB HBM480GB HBM3
Bandwidth7.37 TB/s19.6 TB/s—
Price——$25–40K
VendorGoogleAMDNVIDIA
CategoryGPU & AI ChipsGPU & AI ChipsGPU & AI Chips
OfficialGoogle ↗AMD ↗NVIDIA ↗

Highlighted rows are where these differ.

TPU v7 Ironwood

  • Requires JAX
  • Not purchasable or on any marketplace

Best for GCP inference.

Full spec sheet →

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 →