# Edge Devices Inference Performance Comparison

arXiv: https://arxiv.org/abs/2306.12093 · HTML: https://mlsanity.com/paper/2306.12093/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 21 Jun 2023.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Hello Edge: Keyword Spotting on Microcontrollers](https://mlsanity.com/paper/1711.07128/) (2017)
- [Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence](https://mlsanity.com/paper/1909.00560/) (2019)
- [BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs](https://mlsanity.com/paper/1907.05047/) (2019)

## Built on by (most cited first, 3 of 3)

- [On the Sustainability of AI Inferences in the Edge](https://mlsanity.com/paper/2507.23093/) (2025)
- [Exploration of TPUs for AI Applications](https://mlsanity.com/paper/2309.08918/) (2023)
- [On the Condition Monitoring of Bolted Joints through Acoustic Emission and Deep Transfer Learning: Generalization, Ordinal Loss and Super-Convergence](https://mlsanity.com/paper/2405.20887/) (2024)

## Abstract (arXiv)

In this work, we investigate the inference time of the MobileNet family, EfficientNet V1 and V2 family, VGG models, Resnet family, and InceptionV3 on four edge platforms. Specifically NVIDIA Jetson Nano, Intel Neural Stick, Google Coral USB Dongle, and Google Coral PCIe. Our main contribution is a thorough analysis of the aforementioned models in multiple settings, especially as a function of input size, the presence of the classification head, its size, and the scale of the model. Since throughout the industry, those architectures are mainly utilized as feature extractors we put our main focus on analyzing them as such. We show that Google platforms offer the fastest average inference time, especially for newer models like MobileNet or EfficientNet family, while Intel Neural Stick is the most universal accelerator allowing to run most architectures. These results should provide guidance for engineers in the early stages of AI edge systems development. All of them are accessible at https://bulletprove.com/research/edge_inference_results.csv