MLPerf Client

MLPerf Client is a benchmark developed collaboratively at MLCommons to evaluate the performance of large language models (LLMs) and other AI workloads on personal computers–from laptops and desktops to workstations. The LLM tests in MLPerf Client make use of several different  language models capable of performing a range of tasks based on natural-language interactions, from chat to summarization, code analysis, and more.

Thanks to broad industry collaboration, MLPerf Client supports many types of hardware acceleration–from NPUs to GPUs and hybrid execution. The MLPerf Client working group intends for this benchmark to drive innovation and foster competition, ensuring that personal computers can meet the challenges of the AI-powered future.