The AI PC era dawns, behold the swift new test.

The MLCommons, an industry consortium focused on AI benchmarking, has announced a new effort to benchmark artificial intelligence on personal computers. This comes in anticipation of the “AI PC,” a concept being pursued by leading PC manufacturers Intel and Advanced Micro Devices (AMD). The benchmark, called MLPerf Client, will rate how well chips and systems perform with generative AI on desktops, laptops, and workstations. The initial focus of the benchmark will be on measuring the speed of making predictions, or inference, rather than training. The first benchmark test will involve tasks using Meta’s open-source Llama 2 large language model. The MLPerf Client working group is co-chaired by representatives from Intel, Microsoft, and NVIDIA.