# Performance Options & Specs

Vagon performance options define the cloud hardware available to your computer. Choose the option that matches your workload instead of only choosing the largest available machine, and adjust it whenever your needs change.

## Choosing a Performance Option

Use a stronger performance option for:

* GPU rendering.
* 3D design and visualization.
* Video workflows.
* Large scenes or datasets.

Use a lighter option for:

* General productivity.
* Browser-based work.
* Lightweight design or review workflows.

Vagon groups its hardware into two main categories. Within Graphics Accelerated, there is a latest-generation line built on NVIDIA RTX A10G GPUs and a standard line on NVIDIA Tesla T4 GPUs. Computing Accelerated covers high-frequency CPU options without dedicated GPUs.

{% hint style="info" %}
Hourly rates vary by performance tier and by region. For current pricing in your region, see [vagon.io/pricing](https://vagon.io/pricing) and [vagon.io/region-prices](https://vagon.io/region-prices).
{% endhint %}

## Graphics Accelerated — Latest Generation (RTX A10G)

Built on the NVIDIA A10G Tensor Core GPU. These tiers are the strongest option for GPU rendering, real-time 3D, ray tracing, and complex video workflows.

| Tier      | CPU      | GPU            | RAM    |
| --------- | -------- | -------------- | ------ |
| **Spark** | 4 cores  | 24 GB A10G     | 16 GB  |
| **Flame** | 8 cores  | 24 GB A10G     | 32 GB  |
| **Blaze** | 16 cores | 24 GB A10G     | 64 GB  |
| **Lava**  | 48 cores | 4 × 24 GB A10G | 192 GB |

{% hint style="info" %}
Blaze is a strong default for complex 3D scenes and video work. Step up to Lava when you need multi-GPU rendering or very large scenes.
{% endhint %}

## Graphics Accelerated — Standard (Tesla T4)

Built on the NVIDIA Tesla T4 GPU. A reliable, lower-cost path for everyday graphics workloads.

| Tier       | CPU      | GPU                | RAM    |
| ---------- | -------- | ------------------ | ------ |
| **Planet** | 4 cores  | 16 GB Tesla T4     | 16 GB  |
| **Star**   | 16 cores | 16 GB Tesla T4     | 64 GB  |
| **Galaxy** | 48 cores | 4 × 16 GB Tesla T4 | 192 GB |

Planet is the trial entry point and a cost-effective tier for daily graphics work that does not need the latest-generation GPU.

## Computing Accelerated

High-frequency Intel CPUs without a dedicated GPU. Suitable for compute-heavy workloads, general productivity, and CPU-bound development.

| Tier      | CPU                | RAM    |
| --------- | ------------------ | ------ |
| **Sand**  | 2 cores @ 3.1 GHz  | 4 GB   |
| **Lake**  | 2 cores @ 4.0 GHz  | 16 GB  |
| **Sea**   | 8 cores @ 4.0 GHz  | 64 GB  |
| **Ocean** | 24 cores @ 4.0 GHz | 192 GB |

{% hint style="info" %}
Computing Accelerated tiers have no dedicated GPU. If your application requires a GPU for rendering, real-time 3D, or video acceleration, pick a Graphics Accelerated tier instead.
{% endhint %}

## Changing Performance

You are not locked into a single performance tier. You can upgrade or downgrade your Vagon Computer at any time while keeping the same data, files, and installed applications. The Vagon team compares this to "modifying your car in a racing game" – the vehicle stays yours, the parts change.

To change the performance option:

1. Open your **Dashboard** and select the computer you want to change.
2. Make sure the computer is **stopped**. You cannot change performance while a session is running.
3. Click **Change** next to the current performance option.
4. Pick the new tier and click **Save**.
5. Start the computer again to use the new hardware.

![Open the performance settings from the Dashboard](/files/CkMKTyhMxLRdlWgd2nW1)

![Select a new performance tier and save](/files/c8qz71EoRrRthFFvSCw9)

{% hint style="info" %}
Start with a lighter option for setup, installation, and downloads, then upgrade to a stronger option when you are ready to render or run heavier workloads. Pricing changes with the tier you choose and varies by region – check the live rates at [vagon.io/pricing](https://vagon.io/pricing) and [vagon.io/region-prices](https://vagon.io/region-prices) before starting long sessions.
{% endhint %}

## Next Steps

{% content-ref url="/pages/jUyY3e46bN7chxmKnLiM" %}
[How to Use Vagon Computers](/computer/introduction/how-to-use-vagon-computers.md)
{% endcontent-ref %}

{% content-ref url="/pages/BFi4Fi2Y15LM3l9Mzdga" %}
[Computer Plans](/computer/plans-and-billing/computer-plans.md)
{% endcontent-ref %}

{% content-ref url="/pages/Euj9ioJdqhUxCYMbWepx" %}
[Credits and Balance](/computer/plans-and-billing/credits-and-balance.md)
{% endcontent-ref %}

{% content-ref url="/pages/PiN6uprcnzayurXd7PCc" %}
[Preinstall App Catalog](/computer/features/preinstall-app-catalog.md)
{% endcontent-ref %}


---

# 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://docs.vagon.io/computer/features/performance-options-and-specs.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.