# Managing LLM Models

**Monitoring Model Performance**

1. Navigate to the Dashboards section.
2. Here you can monitor:
   * GPU utilization
   * Memory usage
   * Request throughput
   * Average response time
   * Error rates

**Updating Model Settings**

1. From the model's detail page, click on **Edit Settings**.
2. Modify parameters as needed.
3. Click **Save Changes** to apply.

**Stopping or Restarting Models**

1. From the **Models** list, find the model you want to manage.
2. Use the action menu (typically three dots or a gear icon) to:
   * **Stop Model**: Temporarily shut down the model to free up GPU resources
   * **Restart Model**: Reload the model if you encounter issues
   * **Delete Model**: Completely remove the model from your system


---

# 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://soika-labs.gitbook.io/soika-mockingjay/soikastack-adding-llm-models-and-generating-api-keys/managing-llm-models.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.