Here are the minimum system requirements for the UL Procyon AI Computer Vision Benchmark tests.
Please note that the different inference engines used in the tests have different System requirements.
Windows System Requirements
| OS | Windows 11 Version 24H2 (build 26100) or later |
| Memory | 8 GB RAM |
Windows Inference Engine System Requirements
Qualcomm SNPE & WinML QNN Execution Provider
| SoC | Snapdragon X Elite SoC or later |
| Memory | 16 GB RAM |
Intel OpenVINO & WinML with OpenVINO Execution Provider
| Hardware | Intel NPU, Intel integrated GPU, or Intel dedicated GPU. |
| Memory | 8 GB RAM (Intel NPU or Integrated GPU)
8 GB VRAM (Intel dedicated GPU) |
NVIDIA TensorRT
| Graphics Card | NVIDIA 20 series or later |
| Graphics Memory | 6 GB VRAM |
*For more information on supported GPUs, please refer to the compute capability page on the NVIDIA website.
WinML with NvTensorRtRtx Execution Provider
| Graphics Card | NVIDIA 30 series or later |
| Graphics Memory | 8 GB VRAM |
*For more information on supported GPUs, please refer to the compute capability page on the NVIDIA website.
WinML with VitisAI Execution Provider
| Hardware | AMD XDNA2 NPU or later |
| Memory | 8 GB RAM |
WinML with DirectML Execution Provider
| Hardware | AMD GPU supporting DirectX 12 or later
|
| Graphics Memory | 4 GB RAM |
macOS System Requirements
| OS | macOS Tahoe or later |
| Memory | 8 GB |
macOS Inference Engine System Requirements
Apple Core ML
| Processor | Apple Silicon SoC |
