The answer is the number of replicas in the endpoint, specifically the minimum and maximum nodes configured for autoscaling. These settings directly control the compute instances provisioned for prediction requests, where a higher minimum node count raises baseline cost but reduces cold-start latency, while a lower maximum can cause request queuing and higher latency under load. On the Google Professional Machine Learning Engineer exam, this tests your understanding of how Vertex AI prediction latency and cost configuration settings trade off against each other in production deployments. A common trap is focusing only on machine type or model size, but autoscaling parameters are the primary levers for balancing responsiveness and expense. Remember the memory tip: “Min for money, Max for misery”—a high minimum costs more but keeps latency low, while a low maximum saves money but risks latency spikes under traffic.
PMLE Solving business challenges with ML Practice Question
This PMLE practice question tests your understanding of solving business challenges with ml. This is a configuration task: choose the command set that satisfies every stated requirement. Small differences — like 'secret' vs 'password' or 'transport input ssh' vs 'all' — change whether the answer is correct. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
A team is deploying a model on Vertex AI Prediction. Which THREE configuration settings have a direct impact on both latency and cost? (Choose THREE.)
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Minimum and maximum number of nodes (autoscaling)
Option B is correct because the minimum and maximum number of nodes in autoscaling directly control how many compute instances are provisioned to handle prediction requests. A higher minimum node count increases baseline cost and reduces cold-start latency, while a lower maximum can cause queuing and higher latency under load, directly impacting both metrics.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
✗
Size of training dataset
Why it's wrong here
Does not affect serving latency or cost directly.
✓
Minimum and maximum number of nodes (autoscaling)
Why this is correct
More nodes lower latency but increase cost.
Related concept
Read the scenario before looking for a memorised answer.
✓
Machine type (e.g., n1-standard-2)
Why this is correct
Faster machine reduces latency but increases cost.
Related concept
Read the scenario before looking for a memorised answer.
✗
Model architecture (e.g., number of layers)
Why it's wrong here
Architecture is fixed before deployment; not a config setting for serving endpoints.
✓
Number of replicas in the endpoint
Why this is correct
Replicas affect throughput and cost.
Related concept
Read the scenario before looking for a memorised answer.
Common exam traps
Common exam trap: answer the scenario, not the keyword
Google Cloud often tests the distinction between model-level properties (architecture, training data) and deployment-level configuration settings (machine type, replicas, autoscaling) to see if candidates confuse model development with serving infrastructure.
Detailed technical explanation
How to think about this question
Vertex AI Prediction uses autoscaling based on the 'minReplicaCount' and 'maxReplicaCount' parameters in the endpoint configuration. The machine type (Option C) determines the vCPU, memory, and GPU resources per node, directly affecting per-request latency and per-node cost. The number of replicas (Option E) defines the fixed or autoscaled instance count; more replicas reduce latency under load but increase cost linearly. Under the hood, Vertex AI uses a load balancer to distribute requests across replicas, and the autoscaler adjusts based on CPU utilization or request count, with a cooldown period that can cause latency spikes if minReplicas is set too low.
KKey Concepts to Remember
Read the scenario before looking for a memorised answer.
Find the constraint that changes the correct option.
Eliminate answers that are true in general but not in this case.
TExam Day Tips
→Watch for words such as best, first, most likely and least administrative effort.
→Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
A startup's cloud architect reviews their monthly bill and notices costs are higher than expected for a long-running batch job. Switching from on-demand instances to Reserved Instances — or using Spot/Preemptible VMs — can reduce compute costs by up to 72 %. Questions like this test whether you understand the tradeoffs between commitment, flexibility, and cost across cloud pricing models.
What to study next
Got this wrong? Here's your next step.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Solving business challenges with ML — This question tests Solving business challenges with ML — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Minimum and maximum number of nodes (autoscaling) — Option B is correct because the minimum and maximum number of nodes in autoscaling directly control how many compute instances are provisioned to handle prediction requests. A higher minimum node count increases baseline cost and reduces cold-start latency, while a lower maximum can cause queuing and higher latency under load, directly impacting both metrics.
What should I do if I get this PMLE question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
What is the key concept behind this question?
Read the scenario before looking for a memorised answer.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
This PMLE practice question is part of Courseiva's free Google Cloud certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the PMLE exam.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.