Quick Answer
The answer is to optimize the model using TensorFlow Lite and convert it to a smaller format. This directly addresses the root cause of the latency spike—a 500MB ensemble model that overwhelms real-time inference constraints—by applying techniques like quantization and pruning to reduce computational overhead and model size, which lowers inference latency. On the Google Professional Machine Learning Engineer exam, this scenario tests your ability to prioritize model optimization over infrastructure scaling; a common trap is to suggest adding more Vertex AI nodes, which only masks the inefficiency. Remember the memory tip: "Shrink before you scale"—always optimize the model first when latency is tied to size and complexity, as TensorFlow Lite’s tflite model optimization latency improvements are designed for sub-100ms predictions in production.
This PMLE practice question tests your understanding of serving and scaling 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.
A financial services company deploys a fraud detection model on Vertex AI. The model must make predictions in under 100ms. After deployment, latency spikes to 300ms during peak hours. The model is a large ensemble with 500MB size. Which action is most likely to reduce latency?
Clue words in this question
Noticing these words before you look at the options changes how you read each choice.
Clue: "most likely"
Why it matters: Probability qualifier — the question wants the most probable cause or outcome, not a guaranteed one. Eliminate low-probability options.
Optimize the model using TensorFlow Lite and convert to a smaller format.
Reduces model size and inference time.
Switch to batch prediction to process requests asynchronously.
Why wrong: Batch prediction is not real-time.
Reduce the machine type to a smaller instance.
Why wrong: Less compute power increases latency.
Increase the number of replicas on the endpoint.
Why wrong: Helps with throughput, not per-request latency.
Answer choices
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
Optimize the model using TensorFlow Lite and convert to a smaller format.
The primary cause of latency is the large model size (500MB) combined with real-time inference constraints. Optimizing the model with TensorFlow Lite reduces the model size and computational overhead, directly decreasing inference time. This addresses the root cause—model complexity—rather than scaling infrastructure around an inefficient model.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
For each option: why learners choose it and why it is or isn't the right answer here.
Optimize the model using TensorFlow Lite and convert to a smaller format.
Why this is correct
Reduces model size and inference time.
Clue confirmation
The clue word "most likely" in the question point toward this answer.
Related concept
Read the scenario before looking for a memorised answer.
Switch to batch prediction to process requests asynchronously.
Why it's wrong here
Batch prediction is not real-time.
Reduce the machine type to a smaller instance.
Why it's wrong here
Less compute power increases latency.
Increase the number of replicas on the endpoint.
Why it's wrong here
Helps with throughput, not per-request latency.
Common exam traps
The trap here is that candidates often confuse scaling (replicas or instance size) with optimization, failing to recognize that model size and inference efficiency are the primary drivers of latency in real-time serving.
Detailed technical explanation
TensorFlow Lite applies quantization (e.g., FP32 to FP16 or INT8) and operator fusion, reducing model size by up to 75% while maintaining accuracy. On Vertex AI, deploying a TFLite model uses a specialized runtime that leverages hardware accelerators like TPUs or GPUs more efficiently. In practice, a 500MB ensemble might drop to ~125MB, cutting inference time from 300ms to under 50ms on a CPU-only instance.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
A cloud solutions architect for a retail company is evaluating services for a new workload. The correct answer here reflects best practice for the specific scenario described — not a general cloud recommendation. Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option. Cloud exam questions reward reading the constraint carefully: the same technology can be right or wrong depending on the use case.
What to study next
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Serving and scaling models — study guide chapter
Learn the concepts, then practise the questions
Serving and scaling 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
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Practise PMLE questions linked to Scaling prototypes into ML models.
Practise PMLE questions linked to Automating and orchestrating ML pipelines.
Practise PMLE questions linked to Collaborating within and across teams to manage data and models.
Practise PMLE questions linked to Architecting low-code ML solutions.
Practise PMLE questions linked to Collaborating to manage data and models.
Practise PMLE questions linked to Serving and scaling models.
Practise PMLE questions linked to Monitoring ML solutions.
Practise PMLE questions linked to Solving business challenges with ML.
Practise PMLE questions linked to PMLE fundamentals.
Practise PMLE questions linked to PMLE scenario.
Practise PMLE questions linked to PMLE troubleshooting.
Practice this exam
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Serving and scaling models — This question tests Serving and scaling models — Read the scenario before looking for a memorised answer..
The correct answer is: Optimize the model using TensorFlow Lite and convert to a smaller format. — The primary cause of latency is the large model size (500MB) combined with real-time inference constraints. Optimizing the model with TensorFlow Lite reduces the model size and computational overhead, directly decreasing inference time. This addresses the root cause—model complexity—rather than scaling infrastructure around an inefficient model.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Yes — watch for: "most likely". Probability qualifier — the question wants the most probable cause or outcome, not a guaranteed one. Eliminate low-probability options.
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.