> ## Documentation Index
> Fetch the complete documentation index at: https://docs.siray.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# GPU Quickstart

> Deploy a remote GPU in minutes.

Follow this guide to learn how to create an account and deploy your first GPU instance to use in minutes.

## **Step 1: Create an account**

Start by creating a Siray account:

1. [**Sign up here**](https://www.siray.ai?ytag=doc_quickstart_gpu_instance_1105).
2. If you registered using an email address, please **check your inbox** and complete the verification process before logging in.

## **Step 2: Deploy an instance**

Now that you’ve created your account, you’re ready to deploy your first GPU instance:

1. Open the [**Console page**](https://console.siray.ai/) in the web interface.
2. Select **RTX 4090** from the list of graphics cards.
3. Modify **Instance Configuration**.
4. Click **Deploy** to start your instance. You’ll be redirected back to the instance page after a few seconds.

<Info>
  ### **Terminology**

  * **Container Image**: Docker-compatible OCI image reference.
  * **HTTP/TCP Ports**: Network endpoints exposed by containers for communication. HTTP ports for web services, TCP ports for general network protocols.
  * **Container/System Disk**: Root filesystem partition containing OS and system binaries. Mounted as read-write at container startup but non-persistent across instance restarts.
  * **Volume/Data Disk**: High-performance ephemeral storage directly attached to the GPU instance but non-persistent across instance restarts.
  * **Network Volume**: Network-attached storage service that allows users to access and manage data through a network. Data can be stored on remote servers and accessed from any device.
</Info>

## **Step 3: Connect your instance with JupyterLab**

1. Go back to the **Connect** tab, and under **HTTP Services**, click **Jupyter Lab** to open.

<Check>
  Congrats! You just ran your first GPU instance on Siray.
</Check>

## **Step 4: Stop and terminate**

To avoid incurring unnecessary charges, follow these steps to terminate your GPU resources:

1. Return to the [**Instance page**](https://console.siray.ai/instance-list) and click your running instances.
2. Click the **Stop** button to stop your GPUs.
3. Click **More** in the panel and click **Terminate** to confirm.

<Warning>
  Terminating a Pod permanently deletes all data that isn’t stored in a [**network volume**](https://console.siray.ai/network-volume).

  Be sure that you’ve saved any data you might need to access again.
</Warning>

**Need help?**

* Join the Siray community on [**Discord**](https://discord.com/invite/QePXvrWcYJ).
* Submit a support request using our [**contact page**](https://www.siray.ai/contacts/).