Abstract In the past years, multimodal large language models (MLLMs) have demonstrated remarkable performance in tasks such as visual question answering and visual understanding and reasoning. However, the extensive model size and high training and inference costs have hindered the widespread application of MLLMs in academia and industry. Thus, studying efficient and lightweight MLLMs has enormous potential, especially in edge computing scenarios. In this survey, we provide a comprehensive and systematic review of the current state of efficient MLLMs. Specifically, this survey summarizes the tResearch goal: Does applying the PowerInfer optimization strategy to LLaVA result in measurable degradation in VQA accuracy scores on the GQA benchmark compared to full-precision dense inference on single-GPU setups?Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.5/10.