Pyyan / Compare / MI400 vs B200 vs Ascend 950DT vs H100

MI400 vs B200 vs Ascend 950DT vs H100

4 of 5

GPU & AI Chips · verified 24 Sept 2026

×MI400AMDcurrent
×B200NVIDIAcurrent
×HAscend 950DTHuaweicurrent
×H100NVIDIAcurrent
1 slot left
SpecificationMI400B200Ascend 950DTH100
SummaryDouble NVIDIA's memory capacity.The current volume Blackwell part.144GB on Huawei's own HBM, and the part China is building gigawatts around.The workhorse of the previous generation.
Memory432GB HBM4192GB HBM3e144GB HiZQ 2.080GB HBM3
Bandwidth19.6 TB/s—4 TB/s—
Price—$30–50KAbove ¥250,000 (about $37K), reported$25–40K
VendorAMDNVIDIAHuaweiNVIDIA
CategoryGPU & AI ChipsGPU & AI ChipsGPU & AI ChipsGPU & AI Chips
OfficialAMD ↗NVIDIA ↗Huawei ↗NVIDIA ↗

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 →

B200

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

Best for general training.

Full spec sheet →

Ascend 950DT

  • 4 TB/s memory bandwidth and a 2 TB/s interconnect, 2.5x the Ascend 910C
  • HiZQ 2.0 is Huawei's own memory standard rather than a licensed HBM3 or HBM3e part
  • Indicated price rose 20% to 50% in two months to September 2026, on a memory shortage
  • Successor Ascend 960DT pulled forward to Q1 2027, Huawei said on 17 September

Best for serving models where Nvidia cannot be bought.

Full spec sheet →

H100

The workhorse of the previous generation.

Best for value.

Full spec sheet →