# ARM64X Tutorial

## Introduction

Windows SDK provides ARM64X binaries, which are compatible for x86-64, ARM64 and ARM64EC applications on Windows ARM devices.
ARM64X is only supported on SC8380XP (Snapdragon 8cx Gen 4).

## End-to-end HTP inference with ARM64EC qnn-net-run and offline prepared graph

1. Copy the following files to SC8380XP target device

    - $QNN\_SDK\_ROOT/bin/arm64x-windows-msvc/qnn-net-run.exe
    - $QNN\_SDK\_ROOT/lib/arm64x-windows-msvc/QnnHtp.dll
    - $QNN\_SDK\_ROOT/lib/arm64x-windows-msvc/QnnHtpV73Stub.dll
    - $QNN\_SDK\_ROOT/lib/hexagon-v73/unsigned/libQnnHtpV73Skel.so
    - Inception\_v3\_quantized.serialized.bin (See Converting and executing a CNN model with QNN for more details)
2. Run the following inference command on the target device

$ .\qnn-net-run.exe --input_list .\input_list.txt --retrieve_context .\Inception_v3_quantized.serialized.bin --backend QnnHtp.dll
        Copy to clipboard

## End-to-end HTP inference with ARM64EC qnn-net-run and online prepared graph

1. Copy the following files to SC8380XP target device

    - $QNN\_SDK\_ROOT/bin/arm64x-windows-msvc/qnn-net-run.exe
    - $QNN\_SDK\_ROOT/lib/arm64x-windows-msvc/QnnHtp.dll
    - $QNN\_SDK\_ROOT/lib/arm64x-windows-msvc/QnnHtpV73Stub.dll
    - $QNN\_SDK\_ROOT/lib/arm64x-windows-msvc/QnnHtpPrepare.dll
    - $QNN\_SDK\_ROOT/lib/hexagon-v73/unsigned/libQnnHtpV73Skel.so
    - Inception\_v3\_quantized.dll (See Converting and executing a CNN model with QNN for more details,
and use -t windows-x86\_64 when running the qnn-model-lib-generator)
2. Run the following inference command on the target device

$ .\qnn-net-run.exe --input_list .\input_list.txt --model .\Inception_v3_quantized.dll --backend QnnHtp.dll
        Copy to clipboard

## End-to-end HTP inference with ARM64 qnn-net-run and offline prepared graph

1. Copy the following files to SC8380XP target device

    - $QNN\_SDK\_ROOT/bin/aarch64-windows-msvc/qnn-net-run.exe
    - $QNN\_SDK\_ROOT/lib/arm64x-windows-msvc/QnnHtp.dll
    - $QNN\_SDK\_ROOT/lib/arm64x-windows-msvc/QnnHtpV73Stub.dll
    - $QNN\_SDK\_ROOT/lib/hexagon-v73/unsigned/libQnnHtpV73Skel.so
    - Inception\_v3\_quantized.serialized.bin (See Converting and executing a CNN model with QNN for more details)
2. Run the following inference command on the target device

$ .\qnn-net-run.exe --input_list .\input_list.txt --retrieve_context .\Inception_v3_quantized.serialized.bin --backend QnnHtp.dll
        Copy to clipboard

## End-to-end HTP inference with ARM64 qnn-net-run with online prepared graph

1. Copy the following files to SC8380XP target device

    - $QNN\_SDK\_ROOT/bin/aarch64-windows-msvc/qnn-net-run.exe
    - $QNN\_SDK\_ROOT/lib/arm64x-windows-msvc/QnnHtp.dll
    - $QNN\_SDK\_ROOT/lib/arm64x-windows-msvc/QnnHtpV73Stub.dll
    - $QNN\_SDK\_ROOT/lib/arm64x-windows-msvc/QnnHtpPrepare.dll
    - $QNN\_SDK\_ROOT/lib/hexagon-v73/unsigned/libQnnHtpV73Skel.so
    - Inception\_v3\_quantized.dll (See Converting and executing a CNN model with QNN for more details,
and use -t windows-aarch64 when running the qnn-model-lib-generator)
2. Run the following inference command on the target device

$ .\qnn-net-run.exe --input_list .\input_list.txt --model .\Inception_v3_quantized.dll --backend QnnHtp.dll
        Copy to clipboard

## End-to-end HTP inference with x64 qnn-sample-app and offline prepared graph

1. Copy the following files to SC8380XP target device

    - $QNN\_SDK\_ROOT/examples/QNN/SampleApp/build/src/Release/qnn-sample-app.exe (See [Sample App Tutorial: Create and build a sample C++ application](https://docs.qualcomm.com/doc/80-63442-50/topic/sample_app.html) for more details)
    - $QNN\_SDK\_ROOT/lib/arm64x-windows-msvc/QnnHtp.dll
    - $QNN\_SDK\_ROOT/lib/arm64x-windows-msvc/QnnHtpV73Stub.dll
    - $QNN\_SDK\_ROOT/lib/arm64x-windows-msvc/QnnSystem.dll
    - $QNN\_SDK\_ROOT/lib/hexagon-v73/unsigned/libQnnHtpV73Skel.so
    - Inception\_v3\_quantized.serialized.bin (See Converting and executing a CNN model with QNN for more details)
2. Run the following inference command on the target device

$ .\qnn-sample-app.exe --system_library .\QnnSystem.dll --input_list .\input_list.txt --retrieve_context .\Inception_v3_quantized.serialized.bin --backend QnnHtp.dll
        Copy to clipboard

Last Published: Oct 10, 2025

[Previous Topic
Full SampleApp Hibernation Example](https://docs.qualcomm.com/bundle/publicresource/80-63442-50/topics/hibernation.md) [Next Topic
Windows HTP Library Loading Tutorial](https://docs.qualcomm.com/bundle/publicresource/80-63442-50/topics/htp_lib_loading.md)