You are developing a machine learning model. You must inference the machine learning model for testing. You need to use a minimal cost compute target. Which two compute targets should you use? Each…

The correct answer is D. Local web service E. Azure Container Instances. For testing with minimal cost, Local web service (D) runs the model locally on your development machine with zero Azure compute cost - ideal for quick functional testing. Azure Container Instances (E) is a lightweight, serverless container service billed per second with no…

Train and deploy models

Question

You are developing a machine learning model. You must inference the machine learning model for testing. You need to use a minimal cost compute target. Which two compute targets should you use? Each correct answer presents a complete solution. NOTE: Each correct selection is worth one point.

Options

AAzure Machine Learning Kubernetes
BAzure Databricks
CRemote VM
DLocal web service
EAzure Container Instances

How the community answered

(24 responses)

A
4% (1)
B
17% (4)
C
8% (2)
D
71% (17)

Explanation

For testing with minimal cost, Local web service (D) runs the model locally on your development machine with zero Azure compute cost - ideal for quick functional testing. Azure Container Instances (E) is a lightweight, serverless container service billed per second with no infrastructure management, making it the cheapest Azure-hosted option for low-scale testing and dev/QA. Azure Machine Learning Kubernetes (A) is production-grade and expensive to maintain. Azure Databricks (B) is a premium big-data analytics platform, not cost-optimized for inference testing. Remote VMs (C) incur ongoing VM costs even when idle, making them more expensive than ACI for sporadic test workloads.

Topics

#Compute targets#Model inference#Cost optimization#Testing

Community Discussion

No community discussion yet for this question.

Full DP-100 Practice