- A
Change the machine type to a GPU-accelerated machine like n1-standard-4 with a T4 GPU.
Why wrong: XGBoost does not benefit from GPU typically; GPUs are for deep learning. CPU scaling is more appropriate.
- B
Prune the model to reduce size and improve prediction speed.
Why wrong: Prediction time is already 50ms, so pruning may not significantly reduce latency; the bottleneck is throughput.
- C
Enable autoscaling with a minimum of 2 replicas and use a larger machine type (e.g., n1-standard-8) to handle more concurrent requests.
Autoscaling increases replicas to handle load, and a larger machine can process more requests concurrently, reducing queueing time.
- D
Switch from online prediction to batch prediction using Vertex AI Batch Prediction.
Why wrong: Batch prediction is for offline scoring, not real-time.
Quick Answer
The answer is to enable autoscaling with a minimum of 2 replicas and upgrade to a larger machine type like n1-standard-8. This is correct because the bottleneck is not model inference time—which is only 50ms—but rather the inability of a single replica to handle 100 concurrent requests per second without queuing, which inflates total latency beyond 500ms. Scaling out with multiple replicas increases throughput by processing requests in parallel, while scaling up to a larger machine type provides more CPU and memory per replica to reduce queue wait times, keeping end-to-end latency under 200ms. On the Google Professional Machine Learning Engineer exam, this scenario tests your understanding that Vertex AI online prediction latency is often a function of concurrent request handling, not just model speed; a common trap is to optimize the model or switch to batch processing when the real fix is infrastructure scaling. Remember the mnemonic: “50ms inference, 500ms latency—scale out, don’t doubt.”
PMLE Scaling prototypes into ML models Practice Question
This PMLE practice question tests your understanding of scaling prototypes into ml models. Read the scenario carefully and evaluate each option against the stated constraints before committing to an answer. 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.
You are an ML engineer at a fintech company. You have a prototype credit risk model built using XGBoost that achieves high accuracy on historical data. The model is trained on a dataset with 500,000 rows and 50 features. The company wants to deploy this model to production to score loan applications in real-time. The production environment must handle a peak load of 100 requests per second with a latency under 200ms. You have decided to use Vertex AI for deployment. After deploying the model as a Vertex AI endpoint with a single n1-standard-4 machine, you notice that latency exceeds 500ms at peak load and some requests time out. You have verified that the model prediction itself (excluding network overhead) takes about 50ms on average. What should you do to meet the latency and throughput requirements?
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
Enable autoscaling with a minimum of 2 replicas and use a larger machine type (e.g., n1-standard-8) to handle more concurrent requests.
Option C is correct because the latency bottleneck is not the model inference time (50ms) but the inability of a single n1-standard-4 machine to handle 100 concurrent requests per second without queuing. By enabling autoscaling with a minimum of 2 replicas and upgrading to n1-standard-8, you increase both the number of concurrent requests the endpoint can process and the CPU/memory resources per replica, reducing queue wait times and keeping total latency under 200ms. This directly addresses the throughput and latency requirements without changing the model or switching to batch processing.
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.
- ✗
Change the machine type to a GPU-accelerated machine like n1-standard-4 with a T4 GPU.
Why it's wrong here
XGBoost does not benefit from GPU typically; GPUs are for deep learning. CPU scaling is more appropriate.
- ✗
Prune the model to reduce size and improve prediction speed.
Why it's wrong here
Prediction time is already 50ms, so pruning may not significantly reduce latency; the bottleneck is throughput.
- ✓
Enable autoscaling with a minimum of 2 replicas and use a larger machine type (e.g., n1-standard-8) to handle more concurrent requests.
Why this is correct
Autoscaling increases replicas to handle load, and a larger machine can process more requests concurrently, reducing queueing time.
Related concept
Read the scenario before looking for a memorised answer.
- ✗
Switch from online prediction to batch prediction using Vertex AI Batch Prediction.
Why it's wrong here
Batch prediction is for offline scoring, not real-time.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates assume latency issues are always due to model inference speed (leading them to choose GPU or model pruning), when in fact the bottleneck is often the lack of horizontal scaling to handle concurrent requests under load.
Detailed technical explanation
How to think about this question
Vertex AI endpoints use a load balancer that distributes incoming requests to replicas; with a single replica, requests queue up in the container's thread pool, and if the queue depth exceeds the container's capacity, requests time out. Autoscaling with a minimum of 2 replicas and a larger machine type (e.g., n1-standard-8 with 8 vCPUs) allows the endpoint to handle more concurrent requests by increasing both the number of replicas and the per-replica concurrency (via the `maxConcurrentRequests` setting, which defaults to 10 per vCPU). In practice, you should also tune the container's thread pool and set a proper `minReplicas` to avoid cold-start latency during traffic spikes.
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 healthcare organisation deploys an application with a public-facing web tier and a private database tier. The database subnet has no public IP and only accepts connections from the web tier's security group. Questions like this test whether you can design cloud network isolation using VNets/VPCs, subnets, and security group rules.
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.
- →
Scaling prototypes into ML models — study guide chapter
Learn the concepts, then practise the questions
- →
Scaling prototypes into ML models practice questions
Targeted practice on this topic area only
- →
All PMLE questions
506 questions across all exam domains
- →
Google Professional Machine Learning Engineer study guide
Full concept coverage aligned to exam objectives
- →
PMLE practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Related PMLE practice-question pages
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Scaling prototypes into ML models practice questions
Practise PMLE questions linked to Scaling prototypes into ML models.
Automating and orchestrating ML pipelines practice questions
Practise PMLE questions linked to Automating and orchestrating ML pipelines.
Collaborating within and across teams to manage data and models practice questions
Practise PMLE questions linked to Collaborating within and across teams to manage data and models.
Architecting low-code ML solutions practice questions
Practise PMLE questions linked to Architecting low-code ML solutions.
Collaborating to manage data and models practice questions
Practise PMLE questions linked to Collaborating to manage data and models.
Serving and scaling models practice questions
Practise PMLE questions linked to Serving and scaling models.
Monitoring ML solutions practice questions
Practise PMLE questions linked to Monitoring ML solutions.
Solving business challenges with ML practice questions
Practise PMLE questions linked to Solving business challenges with ML.
PMLE fundamentals practice questions
Practise PMLE questions linked to PMLE fundamentals.
PMLE scenario practice questions
Practise PMLE questions linked to PMLE scenario.
PMLE troubleshooting practice questions
Practise PMLE questions linked to PMLE troubleshooting.
Practice this exam
Start a free PMLE practice session
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Questions learners often ask
What does this PMLE question test?
Scaling prototypes into ML models — This question tests Scaling prototypes into ML models — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Enable autoscaling with a minimum of 2 replicas and use a larger machine type (e.g., n1-standard-8) to handle more concurrent requests. — Option C is correct because the latency bottleneck is not the model inference time (50ms) but the inability of a single n1-standard-4 machine to handle 100 concurrent requests per second without queuing. By enabling autoscaling with a minimum of 2 replicas and upgrading to n1-standard-8, you increase both the number of concurrent requests the endpoint can process and the CPU/memory resources per replica, reducing queue wait times and keeping total latency under 200ms. This directly addresses the throughput and latency requirements without changing the model or switching to batch processing.
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 →
Last reviewed: Jun 11, 2026
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.