# Create PersistentVolumeClaim (PVC)

Create a PVC to provide storage for the model cache. If you are using a Linux operating system, then run the following syntax to create the pvc.yaml file.

```bash
nano pvc.yaml
```

If you are using a Windows operating system, open a text editor such as Notepad or Notepad++.

<figure><img src="https://2882153758-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fi9YWb69HFXLHYlXffReU%2Fuploads%2FxtmEterFJMvkYykw6IgF%2Fimage.png?alt=media&#x26;token=df826455-2057-4730-a5d1-962547b5641b" alt="" width="375"><figcaption><p>Text Editor</p></figcaption></figure>

Enter the following syntax.

```yaml
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: llama-31-70b-instruct
  namespace: vllm
spec:
  accessModes:
  - ReadWriteMany
  resources:
    requests:
      storage: 250Gi
  storageClassName: storage-nvme-c1
  volumeMode: Filesystem
```

If you are using a Linux operating system, run the following syntax but If you are using a Windows operating system save the file as pvc.yaml. in CMD, navigate to the folder that contains the pvc.yaml file and run the following syntax.&#x20;

```bash
kubectl apply -f pvc.yaml
```

<figure><img src="https://2882153758-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fi9YWb69HFXLHYlXffReU%2Fuploads%2FnsNSt6trP5zmDEOfPyJa%2Fimage.png?alt=media&#x26;token=b533ccc1-3c5f-46a9-acae-f05ff7e8ab29" alt=""><figcaption><p>Success Create PVC</p></figcaption></figure>

{% hint style="warning" %}
To delete the pvc.yaml configuration that has been applied, run the following syntax.&#x20;

```bash
kubectl delete -f pvc.yaml -n [namespace]
```

**Replace \[namespace] with the namespace you created in the sub-chapter** [**Create Namespace**](https://docs.cloudeka.ai/reference/deployment-llama-3.1-70b-with-vllm-on-kubernetes/create-namespace)**.**
{% endhint %}