Introducing the ultimate speed test for the AI-powered PC era.

TLDR: The computer industry’s leading organization for rating the performance of neural networks, MLCommons, has announced the formation of a new effort to benchmark AI on personal computers. The new MLPerf Client benchmark will rate how well chips and systems perform with generative AI on desktops, laptops, and workstations. The initial benchmarks will focus on measuring how fast computers make predictions, commonly known as “inference.” The first benchmark test of inference will involve tasks using Meta’s open-source Llama 2 large language model. PC sales fell 15% last year, and PC executives are hoping that AI capabilities will revive the market for personal computers.