This article guides you through the process of sideloading models required for Procyon AI Text Generation Benchmark. Note that an active internet connection is still required to run the test. 

TABLE OF CONTENTS

• Models for workload version 1.0.191
  • Models for GPU, ONNX Runtime
  • Models for Intel GPUs, OpenVINO 2026.1 Runtime
  • Models for AMD NPUs, ONNX VitisAI Runtime
  • Models for Intel NPUs, OpenVINO 2026.1 Runtime
  • Models for Qualcomm NPUs, Genie Runtime
• Installing the Models
• Legacy models
  • Models for OpenVINO NPU 2025.4 Runtime Update (Workload 1.0.152)
  • Models for Qualcomm Genie NPU Runtime (Workload 1.0.152)
  • Models for OpenVINO GPU 2025.2 Runtime Update (Workload 1.0.96 & 1.0.152)
  • Models for OpenVINO GPU 2025.0 Runtime Update (Workload 1.0.82)
  • Models for OpenVINO Runtime (launch version, Workload 1.0.73)

Models for workload version 1.0.191

Models for GPU, ONNX Runtime

Models for Intel GPUs, OpenVINO 2026.1 Runtime

Models for AMD NPUs, ONNX VitisAI Runtime

Models for Intel NPUs, OpenVINO 2026.1 Runtime

Models for Qualcomm NPUs, Genie Runtime

Installing the Models

You may choose to download individual models or all, based on your configuration and benchmarking needs. 

1. By default, the benchmark is installed in

%ProgramData%\UL\Procyon\chops\dlc\ai-textgeneration-benchmark\

2. Create a subfolder named "models", if it does not exist;

%ProgramData%\UL\Procyon\chops\dlc\ai-textgeneration-benchmark\models

3. Unzip the downloaded models and copy them over to the models folder. Note that the extracted folders should not contain the prefix "zip_". The models directory with all the downloaded models should look like this; 

Legacy models

Models for OpenVINO NPU 2025.4 Runtime Update (Workload 1.0.152)

Models for Qualcomm Genie NPU Runtime (Workload 1.0.152)

Models for OpenVINO GPU 2025.2 Runtime Update (Workload 1.0.96 & 1.0.152)

Models for OpenVINO GPU 2025.0 Runtime Update (Workload 1.0.82)

Models for OpenVINO Runtime (launch version, Workload 1.0.73)