PMLE Architecting Low-Code ML Solutions Practice Question
A team trained a TensorFlow model locally and wants to deploy it to BigQuery ML for predictions without retraining. They have exported the SavedModel to Cloud Storage. Which statement is correct?
⚠ Common exam trap
The trap is assuming that BigQuery ML requires models to be trained within BigQuery or converted to a proprietary format. In fact, it supports direct import of TensorFlow SavedModels.
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
✓
They can create a model using CREATE MODEL with model_type='tensorflow' and the path to the SavedModel.
BigQuery ML supports importing TensorFlow models in SavedModel format directly using CREATE MODEL with model_type='tensorflow' and the path to the SavedModel in Cloud Storage. This allows you to use the model for prediction in BigQuery without retraining or converting to a native format. The model is imported as a BigQuery ML model and can be used with ML.PREDICT.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
They need to convert the model to a BigQuery ML native format first.
Why it's wrong here
No conversion is required; CREATE MODEL with the TensorFlow model type reads the SavedModel in Cloud Storage directly and registers it for ML.PREDICT. Conversion is tempting because native BigQuery ML models use their own internal representation, but imported TensorFlow models are served as-is without reformatting.
- ✓
They can create a model using CREATE MODEL with model_type='tensorflow' and the path to the SavedModel.
Why this is correct
CREATE MODEL with model_type='tensorflow' imports an existing SavedModel directly from Cloud Storage, so BigQuery ML serves predictions without retraining. This satisfies the stem's constraint: the locally trained TensorFlow artefact is deployed as-is, with no data or training step required in BigQuery.
- ✗
They must first retrain the model using ML.TRAIN on BigQuery.
Why it's wrong here
Retraining is unnecessary: BigQuery ML imports an already-trained TensorFlow SavedModel through CREATE MODEL, then serves predictions without touching the training data. ML.TRAIN builds native models from BigQuery data. Retraining is tempting because most BigQuery ML workflows do train in-database, but imported models bypass that step entirely.
- ✗
They can use ML.PREDICT directly on the SavedModel in Cloud Storage.
Why it's wrong here
ML.PREDICT queries BigQuery ML models or remote models registered through Cloud AI Platform, not raw SavedModel files in Cloud Storage. The SavedModel must first be imported via CREATE MODEL with the TensorFlow model type. Direct scoring of a GCS artefact is tempting because Cloud Storage hosts the export, but BigQuery cannot read it as a model.
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 →
Same concept, more angles
1 more way this is tested on PMLE
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. 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?
hard- A.Import the model into BigQuery ML using CREATE MODEL with model_type='TENSORFLOW'
- B.Use Vertex AI AutoML Tables to retrain the model
- C.Use Cloud Functions to run the model for each prediction request
- ✓ D.Upload the saved model to Vertex AI and create an endpoint for online predictions
Why D: 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.
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.