Federated Learning (FL) has been proposed as a privacy-preserving approach for distributed learning over decentralized resources. While it can be a highly efficient tool for large scale collaborative training of Machine Learning (ML) models, its efficiency may be strongly impacted by a high variability in data distributions among clients. Clustered FL tackles this problem by grouping clients with similar data distributions and training personalized models. Despite increasing model accuracy for federated peers, existing clustering approaches overlook system and infrastructure constraints leading to sustainability problems for resource-constrained devices. This paper introduces a new method for resource-constrained FL clustering. We leverage pre-trained autoencoders to compress client data into low dimensional space and build lightweight embedding vectors used to cluster federated clients. A randomized quantization approach specifically secures the client embedding vectors against data reconstruction. Extensive experiments using a multi-GPU testbed with multiple scenarios introducing concept drift between clients demonstrate the generalitity of our approach to personalized FL. By minimizing the overall system overhead and improving the model convergence, our approach reduces model training cost by up to 1.44× -4.32× communication, 1.03× -2.40× training time compared to IFCA and 1.0× -8.60× communication, 0.87× -8.40× training time compared to LADD to achieve similar accuracy in the different evaluation scenarios. While each of the baselines encounters performance degradation in at least one of the scenarios, our strategy demonstrates top efficiency in all of them.