Hardware requirement: OmniNeural-4B currently runs only on Qualcomm NPUs (e.g., Snapdragon-powered AIPC).
Apple NPU support is planned next.
Installation
arm64 with Qualcomm NPU supportx86_64 with Intel NPU support Follow the steps under “Deploy Section” on Nexa’s model page to complete the installation.
Get an Access Token
- Create a token in the Model Hub
- Log in with your access token:
Windows
Running Your First Model
OmniNeural-4B (Recommended)
Run the flagship OmniNeural model:Windows
Voice Input Mode
Once the model is running, you can record your voice directly in terminal:Windows
File Input
For images and audio, simply drag your files into the command line. Remember to leave space between file paths.Was this page helpful?