# Model Settings

{% hint style="info" %}
Nx Witness, Nx Go and Nx Meta will work in the same way for the configuration.
{% endhint %}

<figure><img src="/files/H88XurRuU5AOv5qCJtNN" alt="Device model pipeline showing People and Vehicles Detection model with sensitivity slider, postprocessor, and model resizing method settings"><figcaption><p>A device with a single model pipeline</p></figcaption></figure>

A model that is active on a device can have multiple settings These settings depend on the capabilities of the model or the server.

When you change one of these settings, the pipeline form will change to indicate that the settings need to be saved manually.

<figure><img src="/files/Q6Utw1aGywRdA5Y8srRa" alt="Device pipeline editor showing Cancel Changes and Save Pipelines buttons highlighted indicating unsaved changes"><figcaption><p>A model pipeline form with changed settings that are not saved yet</p></figcaption></figure>

To save the settings, click the "Save pipelines" button. If you do not want to save the settings, click the "Cancel Changed" button. Navigating away from the device details page will also reset the form without saving the settings.

### Model Sensitivity

The sensitivity slider controls the NMS Threshold (Non Max Suppression). This sets the cut off for when models should not return detections with a probability score below the current threshold value.

This is a setting that is model dependent, so not all models have this option.

### Preprocessor

If the server that the device is connected to has any preprocessors available, they can be selected here.

This is a setting that is server dependent, so moving a device to another server may change the available options.

Additional settings for preprocessors may appear on the [plugin settings](/nx-ai-manager-v6.1.2/nx-ai-manager-plugin/install-plugin/plugin-settings.md) screen depending on the chosen option.

### Postprocessor

If the server that the device is connected to has any postprocessors available, they can be selected here.

This is a setting that is server dependent, so moving a device to another server may change the available options.

Additional settings for postprocessors may appear on the [plugin settings](/nx-ai-manager-v6.1.2/nx-ai-manager-plugin/install-plugin/plugin-settings.md) screen depending on the chosen option.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://nx.docs.scailable.net/nx-ai-manager-v6.1.2/nx-ai-manager-plugin/configure-the-plugin/model-settings.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.