Prebaking the model

Copy the downloaded model into Kubernetes persistent volume claim (PVC) storage to make it available inside the cluster for serving.

Run the prebake script.
```
python3 prebake-models.py --pre-bake
```
When prompted, enter the model directory path. Paste the model path value from the download summary.
```
Enter path to model directory:
```
For example: /home/rtxcoeuser/.../Qwen3-30B-A3B-Instruct-2507/1.
Review the active kubectl context and enter Y to confirm that the context is correct.
```
Current kubectl context: "kubernetes-adminiqk8stest.
iq.idc.coe.hv@iqk8stest.iq.idc.coe.hv"
Is this the correct context? [Y/n]:
```
Warning: If the context is incorrect, enter N and stop. Copying the model to the wrong cluster can cause service disruption.
Review the PVC space summary. Enter y to confirm and start copying.
```
Proceed with file copy operation? [y/N]:
```
PV space information Size

Total PV capacity 500.00 GB

Used space 4.00 KB

Available space 500.00 GB

Remaining after copy 443.11 GB
The tool performs the following actions:
- Creates a temporary pod in the kserve-models namespace.
- Creates the target directory structure in the PVC.
- Copies all model files.
- Verifies the copied files.
- Deletes the temporary pod.

Review the final summary to confirm the operation completed successfully.

The values shown in the following table are example values from a sample model download. The actual values vary depending on the model you select.

The model is now available in your Kubernetes PVC. You can now serve the model in iQ Studio.