This quickstart will walk you through how to install nexaSDK and run OmniNeural model on Qualcomm Snapdragon X Elite laptop.
Hardware requirement: OmniNeural-4B currently runs only on Qualcomm NPUs (e.g., Snapdragon-powered AIPC). Apple NPU support is planned next.

​
Installation

Download Here: Windows installer with Qualcomm NPU support Follow the steps under “Deploy Section” on Nexa’s model page to complete the installation.

​
Get an Access Token

  1. Create a token in the Model Hub
  2. Log in with your access token:
Windows
nexa config set license '<access_token>'

​
Running Your First Model

Run the flagship OmniNeural model:
Windows
nexa infer omni-neural

​
Voice Input Mode

Once the model is running, you can record your voice directly in terminal:
Windows
> /mic

​
File Input

For images and audio, simply drag your files into the command line. Remember to leave space between file paths.