Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)
Preprint
Abstract
This paper presents PICO-TINYML-BENCHMARK, a modular and platform-agnostic framework for benchmarking the real-time performance of TinyML models on resource-constrained embedded systems. Evaluating key metrics such as inference latency, CPU utilization, memory efficiency, and prediction stability, the framework provides insights into computational trade-offs and platform-specific optimizations. We benchmark three representative TinyML models -- Gesture Classification, Keyword Spotting, and MobileNet V2 -- on two widely adopted platforms, BeagleBone AI64 and Raspberry Pi 4, using real-world datasets. Results reveal critical trade-offs: the BeagleBone AI64 demonstrates consistent inference latency for AI-specific tasks, while the Raspberry Pi 4 excels in resource efficiency and cost-effectiveness. These findings offer actionable guidance for optimizing TinyML deployments, bridging the gap between theoretical advancements and practical applications in embedded systems.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Efficient Neural Networks for Tiny Machine Learning: A Comprehensive ReviewACM Transactions on Intelligent Systems and Technology, 2026
- Advancements in TinyML: Applications, Limitations, and Impact on IoT DevicesElectronics, 2024
- DTMM: Deploying TinyML Models on Extremely Weak IoT Devices with Pruning2024
- Power-Performance Characterization of TinyML Systems2022
- Edge Computing: Vision and ChallengesIEEE Internet of Things Journal, 2016