# Deploy GPUs on Northflank's managed cloud

You can run GPU workloads on Northflank's managed cloud.

This allows you to use GPU acceleration for your applications and services and only pay for the resources consumed. To deploy GPU workloads on Northflank you must create a GPU-enabled project.

You can deploy combined and deployment services and jobs with GPU access. Northflank GPUs do not currently support timeslicing.

Check the [pricing page](https://northflank.com/pricing) to find out more about GPU pricing.

## Deploy a GPU-enabled project

To deploy GPU workloads on Northflank's managed cloud, you'll first need to create a new project in a GPU-enabled region.

> [!note] 
> [Click here](https://app.northflank.com/s/account/projects/new) to create a project.

1. Navigate to the Northflank dashboard and click **Create Project**

2. Enter a project name

3. Choose **Northflank Cloud** as the deployment target

4. Select a region with GPU enabled

5. Click **Create project**

Any services or jobs deployed in this project will have GPU options available in resources. Different regions may have different availability of specific GPU models.

## Deploy a GPU workload on Northflank

To deploy workloads with GPU access:

> [!note] 
> [Click here](https://app.northflank.com/s/project/create/service) to create a service.

1. Navigate to the **Services** tab in your project dashboard and click **Create service**

2. Enter a service name and configure your deployment source as described in [Build and deploy your code](/docs/v1/application/getting-started/build-and-deploy-your-code)

3. Scroll to the **Resources** section and click the **GPU** tab

4. Select an available GPU model from the dropdown (e.g., NVIDIA L4). Each model shows VRAM and hourly pricing

5. Choose the number of GPUs per instance: 1, 2, 4, or 8

6. Review the pricing estimate displayed (billed by the second once provisioned)

7. Configure your **Compute plan** with appropriate CPU and memory for your workload

8. Set the number of **Instances** and autoscaling settings

9. Click **Create service**

Note: GPU deployments require account credit. Ensure you have at least $50 in credit before deploying. Each instance will have access to the GPU count you selected.

| GPU Count | Instances deployed | GPUs per instance | Total GPUs in the service |
| --- | --- | --- | --- |
| 1 | 1 | 1 | 1 |
| 4 | 1 | 4 | 4 |
| 8 | 2 | 8 | 16 |

You may need to configure your workload to make use of GPU hardware, or multiple GPUs.

## Next steps

- [Configure applications to use GPUs: You can directly deploy or build your applications with Docker images that are optimised for your desired GPU model and AI/ML libraries.](/v1/application/gpu-workloads/configure-and-optimise-workloads-for-gpus#configure-applications-to-use-gpus)
- [Build with GPU-optimised images: You can directly deploy or build your applications with Docker images that are optimised for your desired GPU model and AI/ML libraries.](/v1/application/gpu-workloads/configure-and-optimise-workloads-for-gpus#build-with-gpu-optimised-images)
- [Right-size resources for GPU workloads: Scale CPU, memory, and ephemeral storage to handle GPU workloads.](/v1/application/gpu-workloads/configure-and-optimise-workloads-for-gpus#right-size-resources)
- [Persist models and data: You can directly deploy or build your applications with Docker images that are optimised for your desired GPU model and AI/ML libraries.](/v1/application/gpu-workloads/configure-and-optimise-workloads-for-gpus#persist-models-and-training-data)