Best no-code iOS deployment for low latency and cost?

You work for a social media company. You want to create a no-code image classification model for an iOS mobile application to identify fashion accessories. You have a labeled dataset in Cloud Storage. You need to configure a training workflow that minimizes cost and serves predictions with the lowest possible latency. What should you do?

Train the model by using AutoML, and register the model in Vertex AI Model Registry. Configure your mobile application to send batch requests during prediction.
Train the model by using AutoML Edge, and export it as a Core ML model. Configure your mobile application to use the .mlmodel file directly. Source Reference Answer
Train the model by using AutoML Edge, and export the model as a TFLite model. Configure your mobile application to use the .tflite file directly.
Train the model by using AutoML, and expose the model as a Vertex AI endpoint. Configure your mobile application to invoke the endpoint during prediction.

Community Votes

100%

100% of anonymous learners picked answer B. Votes are pick records left by other test-takers — they are not the verified answer.

Community Insight

This question tests the selection of the correct deployment target (Edge) and format (Core ML) for iOS to optimize performance and cost, where the trap is choosing cloud endpoints or non-native formats like TFLite.

To achieve the lowest latency and cost for an iOS image classification app, use AutoML Edge to train and export a Core ML model. The community agrees that on-device inference using Core ML eliminates cloud costs and network delays.

Choosing Option D (Vertex AI endpoint) is a common mistake because while it offers a managed service, it introduces network latency and recurring costs compared to on-device inference.

Community Discussion (8 comments)

forport 👍 1 Selected: B

'for ios mobile' = edge '.mlmodel directly' = minimizes the cost

fitri001 👍 2 Selected: B

No-code Training: AutoML Edge simplifies model training without needing extensive coding knowledge. On-device Processing: Core ML models run directly on the iOS device, minimizing latency by eliminating the need for network calls to a cloud endpoint. Cost-effective: Training on AutoML Edge and deploying the model on the device avoids ongoing costs associated with Vertex AI endpoints.

pinimichele01 👍 1 Selected: B

Core ML is specifically designed for iOS devices, ensuring efficient inference and low latency.

guilhermebutzke 👍 1 Selected: B

My Answer: B AutoML Edge or Vertex AI endpoint?: This option is specifically designed for training models that run on edge devices like mobile phones. It optimizes models for size and efficiency, minimizing cost and latency. While AutoML can train the model, using a Vertex AI endpoint adds unnecessary overhead and potential latency for mobile predictions. Batch requests wouldn't significantly improve latency here. Core ML or TFLite: While TFLite is compatible with some mobile platforms, Core ML is specifically designed for iOS and offers better performance and integration.

b1a8fae 👍 1 Selected: B

B. Confused as AutoML Vision Edge seems like the right tool for this problematic but is deprecated according to docs: https://firebase.google.com/docs/ml/automl-image-labeling I will assume that the question needs updating but we should go with that + core ML is specifically designed for iOS apps. https://www.netguru.com/blog/coreml-vs-tensorflow-lite-mobile

BlehMaks 👍 2 Selected: B

it's possible to use either Core ML or TF Lite, but since it's necessary to ensure the lowest possible latency, choose Core ML https://cloud.google.com/vertex-ai/docs/export/export-edge-model#classification

36bdc1e 👍 1

B For no code , automl is the best , for minimizing the cost we export as Core ML model

pikachu007 👍 2 Selected: B

No-code model development: AutoML Edge provides a no-code interface for model training, aligning with the requirement. Optimized for mobile devices: Core ML is specifically designed for iOS devices, ensuring efficient inference and low latency. Offline capability: The app can run predictions locally without requiring network calls, reducing costs and ensuring availability even without internet connectivity. No ongoing endpoint costs: Unlike using a Vertex AI endpoint, there are no extra costs associated with hosting and serving the model.

Comments & Corrections

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

Expert Analysis

Why the Answer Is Correct

AutoML Edge provides the necessary no-code training capability while optimizing models for edge devices. Exporting the model as a Core ML file allows it to run natively on iOS hardware, leveraging the Neural Engine for the lowest possible latency. By running the model directly on the device, you avoid the recurring costs associated with hosting a cloud endpoint on Vertex AI.

Why the Other Options Are Wrong

Option A suggests batch requests, which are unsuitable for real-time mobile interactions and do not guarantee low latency. Option C uses TFLite, which is compatible with iOS but Core ML is the native, more optimized framework for Apple devices. Option D involves a Vertex AI endpoint, which introduces network latency and ongoing infrastructure costs, violating the requirements for minimizing cost and latency.

Community Comment Notes

Commenters emphasize that Core ML is specifically designed for iOS to ensure efficient inference and low latency. There is a strong consensus that on-device processing removes the need for network calls, which is critical for performance. Additionally, users noted that while AutoML Vision Edge has some deprecation notices in documentation, it remains the correct logical choice for this specific exam scenario.

Official Reference

Exam Strategy

When exam questions specify "lowest latency" and "mobile," prioritize on-device inference over cloud endpoints. If the platform is iOS, always choose Core ML over TFLite for maximum optimization.

Related Analysis

Practice All PMLE Questions

Access 65 questions with complete answers and detailed explanations.

View Full PMLE Practice Test →

← Back to PMLE Study Guide