VM Size depending on model

### Describe your suggestion

On this notebook:
https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/system/inference/text-generation/llama-safe-online-deployment.ipynb

You mention:
sku_name = "Standard_NC24s_v3" # Name of the sku(instance type) Check the model-list(can be found in the parent folder(inference)) to get the most optimal sku for your model (Default: Standard_DS2_v2)

There is no model-list file or folder in the inference folder.

Can you please describe how to know which VM size will suffice for a model? I dont have quota for GPUs for example, any other memory optmized would work? how can I know this?

### Additional details

_No response_