To help MLOps engineers decide which operator to use in which deployment scenario, this study aims to empirically assess the accuracy vs latency trade-off of white-box (training-based) and black-box operators (non-training-based) and their combinations in an Edge AI setup. We perform inference experiments including 3 white-box (i.e., QAT, Pruning, Knowledge Distillation), 2 black-box (i.e., Partition, SPTQ), and their combined operators (i.e., Distilled SPTQ, SPTQ Partition) across 3 tiers (i.e., Mobile, Edge, Cloud) on 4 commonly-used Computer Vision and Natural Language Processing models toResearch goal: How does the trade-off between model size and latency compare between OpenPangu-7B-MLA and smaller prosody-exclusive models when deployed on edge devices for real-time EchoMind classification, and what is the impact on accuracy under fixed hardware constraints?Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.5/10.