Microsoft sets AI inference speed record with Azure ND GB300 v6 VMs, achieving 1.1M tokens/sec using Nvidia GB300 GPUs.
MLPerf Inference tests see the new Azure ND GB300 v6 VMs achieve token performance that ‘fundamentally alters the calculus of ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback