PMLE Architecting Low-Code ML Solutions Practice Question
A company has a TensorFlow model trained outside of Google Cloud and wants to use it for online predictions on Vertex AI. They have saved the model in SavedModel format. What is the most efficient way to deploy this model?
⚠ Common exam trap
The trap is confusing deployment targets: BigQuery ML is for SQL predictions, Cloud Functions for lightweight tasks, and AutoML for training. The correct choice is Vertex AI for custom model serving.
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
✓
Upload the saved model to Vertex AI and create an endpoint for online predictions
The most efficient way to deploy a TensorFlow SavedModel for online predictions on Vertex AI is to upload the SavedModel to Vertex AI and create an endpoint. Vertex AI supports importing custom models in SavedModel format and deploying them to endpoints for low-latency online predictions. This leverages Vertex AI's managed infrastructure for scaling and serving.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Import the model into BigQuery ML using CREATE MODEL with model_type='TENSORFLOW'
Why it's wrong here
BigQuery ML's TENSORFLOW model type supports batch prediction through ML.PREDICT, not the low-latency online endpoint the scenario requires. It is tempting because it imports SavedModel without retraining, but it is the correct choice when predictions can be served from SQL over BigQuery data rather than a Vertex AI endpoint.
- ✗
Use Vertex AI AutoML Tables to retrain the model
Why it's wrong here
AutoML Tables trains a new model from tabular data, discarding the existing TensorFlow SavedModel and its learned weights. It is tempting because AutoML produces a managed Vertex AI endpoint, but it is the correct choice when no trained model exists and tabular data is available for training from scratch.
- ✗
Use Cloud Functions to run the model for each prediction request
Why it's wrong here
Cloud Functions has request timeouts, cold starts and memory ceilings that prevent serving a TensorFlow SavedModel as a persistent online prediction endpoint. It is tempting because it is serverless and needs no infrastructure, but it is the correct choice for lightweight event-driven glue code, not model hosting.
- ✓
Upload the saved model to Vertex AI and create an endpoint for online predictions
Why this is correct
Vertex AI accepts SavedModel artefacts directly, so uploading the existing model and deploying it to an endpoint avoids retraining or conversion. This is the most efficient route to online predictions for a TensorFlow model trained outside Google Cloud.
Go deeper
Related to this question
About these practice questions
One of 775 original PMLE practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Google Cloud exam blueprint
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.