easyMultiple SelectObjective-mapped
MLA-C01 Practice Question: Deploy a model on SageMaker serverless inference
A company wants to deploy a model on SageMaker serverless inference. Which TWO of the following are limitations of serverless endpoints compared to real-time endpoints? (Choose two.)
⚠ Common exam trap
A common mix-up: candidates confuse cold starts (option A) as a limitation unique to serverless endpoints, but the question asks for limitations compared to real-time endpoints, and cold starts are inherent to serverless, not a comparative limitation; the two correct answers are the specific technical constraints of no GPU support and the 6 GB memory cap.
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
✓
No support for GPU instances
SageMaker serverless inference does not support GPU instances; it only runs on CPU-based instances. This is a fundamental limitation for workloads requiring GPU acceleration, such as deep learning models. In contrast, real-time endpoints support both CPU and GPU instance types.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Cold starts can cause increased latency for infrequent requests
Why it's wrong here
Cold start is a characteristic, not a limitation from an exam perspective; it's a trade-off.
- ✗
Cannot deploy multiple containers in the same endpoint
Why it's wrong here
Serverless endpoints support only one container per endpoint; this is a limitation but not listed as correct here because the question asks for limitations compared to real-time; real-time endpoints also typically have one container per variant. Actually, multi-container is not a standard feature; so E is not a typical comparison. Better to stick with A and B.
- ✓
No support for GPU instances
Why this is correct
Serverless endpoints only support CPU.
- ✓
Maximum memory configuration is 6 GB
Why this is correct
Serverless endpoints have a max memory of 6144 MB (6 GB).
- ✗
No automatic scaling – must be configured manually
Why it's wrong here
Serverless scales automatically based on traffic.
Quick reference
Cloud Service Model Comparison
| Model | You Manage | Provider Manages | Examples |
|---|---|---|---|
| IaaS | OS, runtime, apps, data | Hardware, hypervisor, networking | EC2, Azure VMs, GCP Compute Engine |
| PaaS | Apps and data | OS, runtime, middleware, hardware | Elastic Beanstalk, Azure App Service |
| SaaS | Data and settings only | Everything else | Microsoft 365, Salesforce, Workday |
| FaaS / Serverless | Function code only | Infra, scaling, runtime | Lambda, Azure Functions, Cloud Run |
| CaaS | Containers and apps | Kubernetes, OS, hardware | EKS, AKS, GKE |
Go deeper
Related to this question
About these practice questions
One of 835 original MLA-C01 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 MLA-C01 practice question is part of Courseiva's free Amazon Web Services 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 MLA-C01 exam.