How to Perform Batch Inference on Multi-Terabyte BigQuery Data

You are implementing a batch inference ML pipeline in Google Cloud. The model was developed using TensorFlow and is stored in SavedModel format in Cloud Storage. You need to apply the model to a historical dataset containing 10 TB of data that is stored in a BigQuery table. How should you perform the inference?

  1. Export the historical data to Cloud Storage in Avro format. Configure a Vertex AI batch prediction job to generate predictions for the exported data
  2. Import the TensorFlow model by using the CREATE MODEL statement in BigQuery ML. Apply the historical data to the TensorFlow model Source Reference Answer
  3. Export the historical data to Cloud Storage in CSV format. Configure a Vertex AI batch prediction job to generate predictions for the exported data
  4. Configure a Vertex AI batch prediction job to apply the model to the historical data in BigQuery

Community Votes

B
72%
D
28%

72% of anonymous learners picked answer B. Votes are pick records left by other test-takers — they are not the verified answer.

Community Insight

Tests knowledge of managed ML service constraints versus native SQL-based inference, trapping candidates who assume direct BigQuery integration scales infinitely.

This question evaluates selecting the optimal batch inference architecture for massive datasets in Google Cloud. Community consensus confirms that BigQuery ML is mandatory to bypass Vertex AI's 100 GB input limitation when processing terabytes of structured data.

Option D is frequently selected due to Vertex AI's native BigQuery connector, but it fails because the service strictly caps source table sizes at 100 GB per batch job.

Community Discussion (13 comments)

NamitSehgal 👍 1 Selected: D
Managed Service: Vertex AI batch prediction
lunalongo 👍 1 Selected: A
A) - BigQuery ML is not designed for the scale of a 10TB dataset - Batch Prediction performs efficient batch inference on large GCS datasets - AVRO is a binary format, more compact and efficient to process than CSV *B uses BQML; C uses CSV format; exporting to GCS is more efficient than performing Vertex AI predictions directly on BQ for this volumetry.
rajshiv 👍 1 Selected: A
It should be A. The "CREATE MODEL" statement in BigQuery ML is meant for BigQuery-specific models, and do not support models like TensorFlow SavedModel out of the box. This option would not work for using a TensorFlow model stored in Cloud Storage.
Foxy2021 👍 1
My answer is D.
pinimichele01 👍 1 Selected: B
https://cloud.google.com/vertex-ai/docs/tabular-data/classification-regression/get-batch-predictions#input_data_requirements
edoo 👍 4 Selected: B
The choice is between B and D, both good BUT: Importing and making batch predictions is quite straightforward in BQ ML https://cloud.google.com/bigquery/docs/making-predictions-with-imported-tensorflow-models if not pre-processing needed on the data. If we need a more complete pipeline I'd chose D, but the tables need partitioning (100GB is the limit in Vertex AI): https://cloud.google.com/vertex-ai/docs/tabular-data/classification-regression/get-batch-predictions#input_data_requirements
guilhermebutzke 👍 1 Selected: D
My Answer: D The historical dataset is stored in BigQuery, which can be directly accessed by Vertex AI. Vertex AI offers batch prediction capabilities, allowing you to apply the model to the data stored in BigQuery without the need to export it. So, This approach leverages the scalability of Google Cloud infrastructure and avoids unnecessary data movement, being not necessary to export data to Cloud Store (options A and C), nor Import the TensorFlow model to BQ (option B).
ddogg 👍 2 Selected: B
https://cloud.google.com/bigquery/docs/making-predictions-with-imported-tensorflow-models#:~:text=Import%20TensorFlow%20models,-To%20import%20TensorFlow&text=In%20the%20Google%20Cloud%20console%2C%20go%20to%20the%20BigQuery%20page.&text=In%20the%20query%20editor%2C%20enter,MODEL%20statement%20like%20the%20following.&text=The%20preceding%20query%20imports%20a,BigQuery%20ML%20model%20named%20imported_tf_model%20.
sonicclasps 👍 2 Selected: B
https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-create-tensorflow#limitations
Zwi3b3l 👍 4 Selected: B
Has to be B, because D has limitations: BigQuery data source tables must be no larger than 100 GB. https://cloud.google.com/vertex-ai/docs/tabular-data/classification-regression/get-batch-predictions#input_data_requirements
BlehMaks 👍 1 Selected: A
Same platform as data == less computation required to load and pass it to model
b1a8fae 👍 2 Selected: D
It could either be B or D. It seems like most of the limitations of B are mentioned in the problem (https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-create-tensorflow#limitations) but some of them are not and we are left questioning if the model will match the remaining requirements. Therefore, I would go for D, which can import data from BigQuery. https://cloud.google.com/vertex-ai/docs/predictions/get-batch-predictions#bigquery
pikachu007 👍 1 Selected: D
Limitations of other options: A and C. Exporting data: Exporting 10 TB of data to Cloud Storage incurs additional storage costs, transfer time, and potential data management complexities. B. BigQuery ML: While BigQuery ML supports some TensorFlow models, it might have limitations with certain model architectures or features. Additionally, it might not be as optimized for large-scale batch inference as Vertex AI.

Comments & Corrections

No comments yet — spotted an error or have a note? Share it below.

Log in to comment, report an error, or add a note about this question.

Submitted for moderation before publishing. Keep it helpful and respectful.

Expert Analysis

Why the Answer Is Correct

BigQuery ML enables direct import of TensorFlow SavedModels via the CREATE MODEL statement, allowing predictions to run natively on massive tables. Processing 10 TB of data within BigQuery eliminates data egress costs, reduces pipeline latency, and leverages the platform's distributed compute engine. This approach aligns perfectly with the requirement to apply a pre-trained model to historical tabular data without external orchestration.

Why the Other Options Are Wrong

Options A and C mandate exporting 10 TB of data to Cloud Storage, which introduces prohibitive transfer times, additional storage fees, and complex data management overhead. Option D incorrectly assumes Vertex AI batch prediction can ingest terabyte-scale BigQuery tables directly, overlooking the documented 100 GB maximum limit per input table. Relying on export workflows also fragments the data lifecycle and increases operational maintenance.

Community Comment Notes

Candidates repeatedly identify the 100 GB restriction as the decisive factor distinguishing options B and D [2][9]. Multiple users reference official documentation to validate the TensorFlow import workflow and its compatibility with BigQuery ML [1][3]. While several initially favored Vertex AI for its managed infrastructure, they ultimately acknowledged that dataset volume forces a native SQL-based solution [5][10]. The thread underscores the importance of verifying service quotas before architecting production pipelines.

Official Reference

Exam Strategy

Always verify input data size limits and supported file formats before selecting a managed machine learning service. When handling terabyte-scale tabular datasets, prioritize platforms that compute natively over those requiring data movement or external staging buckets.

Related Analysis

You are investigating the root cause of a misclassification

A-Grade

You work for a hotel and have a dataset that contains custom

S-Grade

You are building a predictive maintenance model to preemptiv

A-Grade

Practice All PMLE Questions

Access 65 questions with complete answers and detailed explanations.

View Full PMLE Practice Test →

← Back to PMLE Study Guide