With the increasing popularity of large deep learning modelserving workloads, there is a pressing need to reduce the energy consumption of a model-serving cluster while maintaining satisfied throughput or model-serving latency requirements. Model multiplexing approaches such as model parallelism, model placement, replication, and batching aim to optimize the model-serving performance. However, they fall short of leveraging the GPU frequency scaling opportunity for power saving. In this paper, we demonstrate (1) the benefits of GPU frequency scaling in power saving for model serving; and (2) the necessity for co-design and optimization of finegrained model multiplexing and GPU frequency scaling. We explore the co-design space and present a novel power-aware model-serving system, µ-Serve. µ-Serve is a model-serving framework that optimizes the power consumption and modelserving latency/throughput of serving multiple ML models efficiently in a homogeneous GPU cluster. Evaluation results on production workloads show that µ-Serve achieves 1.2–2.6x power saving by dynamic GPU frequency scaling (up to 61% reduction) without SLO attainment violations.