Deployment to i.MX 93

eIQ AI Toolkit enables deployment of machine learning models to devices by converting them into a format optimized for NPU-based inference acceleration.

For i.MX 93, an additional conversion step is required. The output remains a quantized TFLite model but is adapted specifically for execution on the NPU.

To complete the conversion process, refer to these guides:

1. Deploying machine learning models to devices – Learn the workflow for converting models to quantized TF Lite.

2. Converting model for i.MX 93 NPU – Perform the final conversion for i.MX 93.