PyyanThe AI Index

Pyyan / Compare / B300 Blackwell Ultra vs B200 vs MI400 vs H100 vs TPU v7 Ironwood

B300 Blackwell Ultra vs B200 vs MI400 vs H100 vs TPU v7 Ironwood

5 of 5

GPU & AI Chips · verified 13 Aug 2026

×B300 Blackwell UltraNVIDIAcurrent
×B200NVIDIAcurrent
×MI400AMDcurrent
×H100NVIDIAcurrent
×TPU v7 IronwoodGooglecurrent
SpecificationB300 Blackwell UltraB200MI400H100TPU v7 Ironwood
Summary15 PFLOPS dense FP4.The current volume Blackwell part.Double NVIDIA's memory capacity.The workhorse of the previous generation.Inference-oriented, Google Cloud only.
Memory288GB HBM3e192GB HBM3e432GB HBM480GB HBM3192GB HBM3e
Bandwidth8 TB/s—19.6 TB/s—7.37 TB/s
Price~$40–50K (verify)$30–50K—$25–40K—
VendorNVIDIANVIDIAAMDNVIDIAGoogle
CategoryGPU & AI ChipsGPU & AI ChipsGPU & AI ChipsGPU & AI ChipsGPU & AI Chips
OfficialNVIDIA ↗NVIDIA ↗AMD ↗NVIDIA ↗Google ↗

Highlighted rows are where these differ.

B300 Blackwell Ultra

  • 8 TB/s memory bandwidth
  • Per-GPU pricing widely misquoted — one source cites rack pricing

Best for frontier training.

Full spec sheet →

B200

  • Sold out through mid-2026
  • ~3.6M unit backlog

Best for general training.

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 →

TPU v7 Ironwood

  • Requires JAX
  • Not purchasable or on any marketplace

Best for GCP inference.

Full spec sheet →