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

# Deploying Instances

> Step-by-step guide to deploying a GPU instance.

export const RuncrateStyles = () => {
  if (typeof document !== 'undefined' && !document.getElementById('runcrate-overrides')) {
    const s = document.createElement('style');
    s.id = 'runcrate-overrides';
    s.textContent = `
      /* Match Runcrate's rounding scale (--radius: 0.75rem) */
      .rounded-sm { border-radius: 0.5rem !important; }   /* 8px */
      .rounded-md { border-radius: 0.625rem !important; } /* 10px */
      .rounded-lg { border-radius: 0.75rem !important; }  /* 12px */
      .rounded-l-sm { border-top-left-radius: 0.5rem !important; border-bottom-left-radius: 0.5rem !important; }
      .rounded-r-sm { border-top-right-radius: 0.5rem !important; border-bottom-right-radius: 0.5rem !important; }
      .rounded-l-md { border-top-left-radius: 0.625rem !important; border-bottom-left-radius: 0.625rem !important; }
      .rounded-r-md { border-top-right-radius: 0.625rem !important; border-bottom-right-radius: 0.625rem !important; }
      .rounded-l-lg { border-top-left-radius: 0.75rem !important; border-bottom-left-radius: 0.75rem !important; }
      .rounded-r-lg { border-top-right-radius: 0.75rem !important; border-bottom-right-radius: 0.75rem !important; }

      /* Cards: never pure white in light mode */
      .card { background-color: #fcfcfc !important; border-radius: 0.75rem !important; }
      html.dark .card { background-color: #141414 !important; }

      /* Docs hero box */
      .rc-hero { background-color: #fcfcfc; border: 1px solid #e0e0e0; }
      html.dark .rc-hero { background-color: #141414; border-color: #242424; }
      html.dark .rc-hero h1 { color: #f5f5f5; }

      /* Runcrate scrollbar — thin, transparent track, hide-until-hover thumb */
      ::-webkit-scrollbar { width: 6px; height: 6px; background-color: transparent; }
      ::-webkit-scrollbar-track { background-color: transparent; }
      ::-webkit-scrollbar-thumb { background-color: rgba(155, 155, 155, 0.5); border-radius: 10px; transition: opacity 0.3s ease; opacity: 0; }
      ::-webkit-scrollbar-thumb:hover { background-color: rgba(155, 155, 155, 0.7); }
      *:hover::-webkit-scrollbar-thumb,
      *:focus::-webkit-scrollbar-thumb,
      *:active::-webkit-scrollbar-thumb { opacity: 1; }
      * { scrollbar-width: thin; scrollbar-color: rgba(155, 155, 155, 0.5) transparent; }
    `;
    document.head.appendChild(s);
  }
  return null;
};

<RuncrateStyles />

This guide walks you through deploying a GPU instance on Runcrate.

## Prerequisites

Before deploying, make sure you have:

* A [Runcrate account](https://runcrate.ai/sign-up)
* **Credits** in your account balance ([add credits here](/billing/overview))
* An **SSH key** added to your account ([manage SSH keys](/account/ssh-keys))

## Step-by-Step Deployment

### 1. Open the Deploy Page

Navigate to **Dashboard** > **Instances** > **Deploy Instance**, or go directly to [runcrate.ai/dashboard/instances/deploy](https://runcrate.ai/dashboard/instances/deploy).

### 2. Choose GPU Type and Count

Select the GPU model that fits your workload. You can deploy multiple GPUs on a single instance for multi-GPU training.

| GPU        | VRAM  | Recommended For                        |
| ---------- | ----- | -------------------------------------- |
| RTX 4090   | 24 GB | Inference, fine-tuning                 |
| L40S       | 48 GB | Large model inference, medium training |
| A100 40 GB | 40 GB | Training, research                     |
| A100 80 GB | 80 GB | Large-scale training                   |
| H100       | 80 GB | Maximum performance                    |

### 3. Configure CPU, Memory, and Storage

Adjust the instance specifications based on your needs:

* **CPU cores** -- More cores help with data preprocessing and multi-threaded workloads.
* **RAM** -- Ensure enough memory for your dataset and model. A good rule of thumb is 2x your GPU VRAM.
* **Disk** -- Local NVMe storage for your code, datasets, and model weights.

### 4. Select a Region

Choose from available regions. Availability of specific GPU types may vary by region.

<Tip>
  Select the region closest to you for the lowest latency SSH experience.
</Tip>

### 5. Choose a Template

Select a pre-built template with the tools you need:

| Image                              | Includes                                                                |
| ---------------------------------- | ----------------------------------------------------------------------- |
| **Devbox** (`ubuntu-devbox`)       | Python + uv, VS Code Server, Jupyter, Docker, SSH                       |
| **Finetune** (`ubuntu-train`)      | Unsloth, PyTorch + CUDA, HuggingFace CLI, W\&B, Jupyter, VS Code Server |
| **Inference** (`ubuntu-inference`) | vLLM or SGLang, HuggingFace CLI, nvtop, Jupyter, VS Code Server         |

### 6. Attach an SSH Key

Select one or more SSH keys to authorize for the instance. If you have not added a key yet, you can do so from **Dashboard** > **SSH Keys**.

### 7. Optionally Attach Storage

You can attach a persistent storage volume to your instance. This keeps your data safe across instance terminations. See [Storage](/storage/overview) for details.

### 8. Review and Deploy

Review your configuration and estimated hourly cost, then click **Deploy**.

## Cost Estimation

Your hourly cost is determined by:

```
Hourly Cost = GPU cost x GPU count + CPU cost + Memory cost + Storage cost
```

The exact cost is displayed on the deploy page before you confirm.

## Deployment Time

Instances typically take **1-3 minutes** to go from `creating` to `deployed`. You will see the status update in real time on the Instances dashboard.

<Tip>
  **Enable auto-recharge** in your [Billing settings](/billing/overview) to ensure your balance never runs out and your instances are not interrupted.
</Tip>

## What Happens Next

Once your instance status shows **Deployed**:

1. Copy the SSH command from the instance details.
2. Connect via terminal or VS Code.
3. Start building.

See [Connecting to Instances](/instances/connecting) for the full connection guide.