# Windows

## Basic Dialog

This section contains tutorials that pertain to running the Llama 2 7B model on HTP within a basic dialog.

## Dialog JSON Configuration

See [Genie Dialog JSON configuration string](https://docs.qualcomm.com/doc/80-63442-10/topic/dialog_json.html#genie-dialog-json-config-string) for details on the fields and what
they mean. An example model\_config can be found at
`${QNN_SDK_ROOT}/examples/Genie/configs/llama2-7b/llama2-7b-htp-windows.json`. Note that the tokenizer path and
context binary fields will need to be updated based on your actual preparation steps.

## Inference

Open `Developer PowerShell for VS2022` on Windows on Snapdragon host and run:

# Make sure environment is setup as per instructions, or can cd into bin folder on Windows host
    cd <QNN_SDK_ROOT>\bin\aarch64-windows-msvc
    .\genie-t2t-run.exe -c <path to llama2-7b-htp.json>
                        -p "Tell me about Qualcomm"
    Copy to clipboard

Last Published: Aug 06, 2026

[Previous Topic
LADE](https://docs.qualcomm.com/bundle/publicresource/80-63442-10/topics/lade.md) [Next Topic
QNN Gen AI Transformer](https://docs.qualcomm.com/bundle/publicresource/80-63442-10/topics/genai.md)