Estimate neural accelerator performance with ML Inference Advisor
Introduction
Understand MLIA and the NX Performance Estimator
Set up your MLIA environment
Download a public baseline model
Check baseline operator compatibility
Estimate baseline performance and inspect reports
Compare a smaller model under the same target profile
(Optional) Run and profile the model on an NX device
Next Steps
Estimate neural accelerator performance with ML Inference Advisor
Introduction
Understand MLIA and the NX Performance Estimator
Set up your MLIA environment
Download a public baseline model
Check baseline operator compatibility
Estimate baseline performance and inspect reports
Compare a smaller model under the same target profile
(Optional) Run and profile the model on an NX device
Next Steps
Who is this for?
This Learning Path is for machine learning (ML) engineers and graphics developers who want to evaluate model compatibility and estimated neural accelerator (NX) performance for Arm Neural Technology before deployment.
What will you learn?
After completing this Learning Path, you'll be able to perform the following tasks:
- Install the public Arm ML Inference Advisor (MLIA) Neural Technology plugin and discover its target profiles and backend.
- Analyze public quantized MobileNet models with automatic model conversion.
- Check operator compatibility and interpret NX Performance Estimator reports.
- Compare model variants under the same target configuration and identify accuracy tradeoffs.
Prerequisites
Before starting, you'll need the following prerequisites:
- An x86-64 Ubuntu 24.04 LTS development host with CPython 3.12
- Basic familiarity with Python, command-line tools, and model deployment
- (Optional) An NX-capable Android device
Summary
This summary was drafted with an approved AI-assisted workflow and reviewed by Arm contributors before publication. Human technical review remains part of the process so the final page reflects engineering rigor, accuracy, and Arm editorial standards.