Generative AI Leader Google Cloud's Generative AI Offerings Practice Question
Which THREE factors should you consider when selecting a foundation model from Model Garden? (Choose three.)
⚠ Common exam trap
The exam tests candidates' ability to distinguish between superficial UI elements (like card color) and substantive technical criteria (like model size, accuracy, and license) that directly affect deployment and compliance.
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
✓
Model size
When selecting a foundation model from Model Garden, model size (C) matters because parameter count directly affects inference latency, throughput, memory footprint, and cost, so it must match your deployment and budget constraints. Model accuracy on benchmarks (D) is essential because benchmark results (e.g., MMLU, GSM8K, HELM scores) indicate how well the model performs on the tasks relevant to your use case. Model license (E) must be evaluated because it determines whether commercial use, redistribution, or fine-tuning is permitted, which directly impacts legal and business viability. The number of model versions (A) is not a primary selection factor since version count alone says nothing about capability, cost, or fit. The color of the model card (B) is purely cosmetic and has no bearing on model selection.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Number of model versions
Why it's wrong here
Version count reflects release history, not whether a model fits the task, cost or latency budget. It is tempting because a frequently updated model can indicate active maintenance, which matters when long-term vendor support and patching are the deciding criteria.
- ✗
The color of the model card
Why it's wrong here
Model card colour is cosmetic documentation styling and carries no information about capability, licensing or performance. It is tempting because model cards themselves are genuinely relevant, listing training data, intended use and limitations, so reviewing the card is correct when assessing suitability and governance.
- ✓
Model size
Why this is correct
Model size determines inference latency, memory footprint and hosting cost, so it must match the deployment target's compute budget and latency requirements. Larger models generally offer greater capability but demand more resources, making size a primary selection constraint.
- ✓
Model accuracy on benchmarks
Why this is correct
Benchmark accuracy indicates how well a foundation model performs on tasks resembling your intended use case, giving an objective basis for comparison. It must be weighed against your specific domain, since strong general benchmarks do not guarantee performance on specialised data.
- ✓
Model license
Why this is correct
The model licence defines permitted commercial use, redistribution and modification rights, so it must be verified before selection. A technically suitable model with restrictive licensing cannot be deployed in products, making licence terms a binding constraint on choice.
Go deeper
Related to this question
About these practice questions
One of 1,008 original Generative AI Leader 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 by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This Generative AI Leader 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 Generative AI Leader exam.