# Prepare models for neural graphics with Arm neural technology

## In this learning path

- [Introduction](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/preparing-models-for-nt/)
- [Set up your environment](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/preparing-models-for-nt/1-setup/)
- [Create a reference model](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/preparing-models-for-nt/2-create-reference-model/)
- [Export the reference model with the ExecuTorch VGF backend](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/preparing-models-for-nt/3-convert-to-vgf-and-validate/)
- [Inspect the model in Model Explorer](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/preparing-models-for-nt/4-inspect-model-explorer/)
- [Inspect TOSA artifacts](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/preparing-models-for-nt/5-extract-tosa-artifacts/)
- [Next Steps](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/preparing-models-for-nt/_next-steps/)

## About this Learning Path

|  |  |
| --- | --- |
| Skill level: | Advanced |
| Reading time: | 45 min |
| Last updated: | 12 Nov 2026 |

|  |  |
| --- | --- |
| Author: | Joshua Marshall-Law , Arm |
| Arm IP: | [Mali](https://support.arm.com/?tab=compute-ip&Product%20Type=Graphics%20Processors) |
| Tags: | [AI/ML](https://learn.arm.com/tag/ai-ml/) [Linux](https://learn.arm.com/tag/linux) [macOS](https://learn.arm.com/tag/macos) [ExecuTorch](https://learn.arm.com/tag/executorch) [PyTorch](https://learn.arm.com/tag/pytorch) [Model Explorer](https://learn.arm.com/tag/model-explorer) [Jupyter Notebook](https://learn.arm.com/tag/jupyter-notebook) [Vulkan](https://learn.arm.com/tag/vulkan) [TOSA](https://learn.arm.com/tag/tosa) [NX](https://learn.arm.com/tag/nx) |

### Who is this for?
This is an advanced topic for developers who want to understand and debug the model preparation flow used by Arm neural technology in neural graphics pipelines.

### What will you learn?
After completing this Learning Path, you'll be able to perform the following tasks:
- Build and export a PyTorch model for ExecuTorch
- Generate `.vgf` artifacts with the ExecuTorch VGF backend
- Visualize model structure and generated artifacts using Model Explorer
- Inspect Tensor Operator Set Architecture (TOSA) intermediate representation when you need to debug operator lowering
- Validate the generated model with an ExecuTorch runner and connect it to ML Extensions for Vulkan workflows

### Prerequisites
Before starting, you'll need the following prerequisites:
- Basic PyTorch and Python experience
- A Linux machine or macOS machine with Apple Silicon
- Python version greater than 3.10 and less than 3.14, and Git installed

### 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.

You’ll prepare a PyTorch model for Arm neural technology by exporting a small `AddSigmoid` reference model with the ExecuTorch VGF backend. First, you’ll set up the required environment, generate `.vgf` and `.pte` artifacts, and optionally validate the `.pte` with the VKML runner. Then, you’ll inspect the artifacts in Model Explorer and extract TOSA artifacts to debug operator lowering, tensor layouts, and shape flow.