We benchmarked five novel edge devices:

• Nvidia Jetson Nano
• Google Coral Dev Board
• Intel Neural Compute Stick
• Raspberry Pi (upper bound reference)
• 2080ti NVIDIA GPU (lower bound reference)

We used different frameworks and models, to see which combinations perform best. In particular, we focused on performance outcomes for machine learning on the edge.

You can see the results here:

• Full article: https://tryolabs.com/blog/machine-learning-on-edge-devices-benchmark-report/
• Results only: https://tryolabs.com/blog/machine-learning-on-edge-devices-benchmark-report/#results-analysis

Edit: Added links to the hardware in question.