CCNA Gcl Google Ai Ecosystem Questions — Page 2 of 2

MCQmedium

A developer is building a real-time speech transcription application for customer support calls. The audio is streamed, and the transcription must be returned with low latency. Which Google Cloud AI service should they use?

A.Natural Language API

B.Cloud Speech-to-Text with streaming recognition

C.Cloud Text-to-Speech

D.Vertex AI with a custom model

AnswerB

Streaming recognition allows for real-time transcription of audio as it is being captured, meeting low-latency requirements.

Why this answer

Speech-to-Text supports streaming recognition, making it suitable for real-time transcription with low latency.

Practice this question →

MCQmedium

A company needs to extract structured data from scanned invoices (invoice number, date, total amount) using a pre-built AI solution. Which Google Cloud service is MOST appropriate?

A.Natural Language AI

B.Translation API

C.Document AI

D.Vision AI

AnswerC

Document AI has pre-trained processors for invoices and other documents.

Why this answer

Document AI is specifically designed for processing documents like invoices and extracting structured data. Vision AI is for general image analysis, Natural Language AI for text, and Translation API for translation.

Practice this question →

Multi-Selectmedium

A company is deploying Gemini in an enterprise application and needs to choose between Gemini Pro and Gemini Flash for cost optimization. The application has high throughput and can tolerate lower latency. Which TWO considerations should guide the choice? (Choose 2)

Select 2 answers

A.Gemini Flash runs on-device for latency-sensitive applications

B.Gemini Nano is the best choice for high-throughput server workloads

C.Gemini Pro provides higher quality outputs at a higher cost

D.Gemini Pro is only available in Google AI Studio

E.Gemini Flash is optimized for lower cost and higher throughput

AnswersC, E

Pro is more capable but more expensive; if the task requires higher quality, Pro may be worth the cost.

Why this answer

Gemini Flash is cost-optimized for high throughput and lower cost, while Gemini Pro offers higher quality but at higher cost. For high volume, cost-efficient inference, Flash is better. If quality is critical, Pro is warranted.

On-device models (Nano) are not relevant here.

Practice this question →

MCQhard

A company is comparing Google Cloud Vertex AI vs AWS Bedrock vs Azure OpenAI. Their application requires grounding responses with real-time search results from the internet. Which platform's feature uniquely supports this requirement?

A.Gemini API without grounding

B.Vertex AI with Grounding + Google Search

C.Azure OpenAI with Bing Search grounding

D.AWS Bedrock with Knowledge Bases

AnswerB

Vertex AI uniquely provides Grounding with Google Search, allowing real-time web results to be incorporated into model responses.

Why this answer

Vertex AI with Grounding + Google Search is the correct answer because it uniquely provides native, real-time grounding against live internet search results via Google Search, enabling the model to retrieve and cite up-to-date information from the web. This feature is directly integrated into Vertex AI's model serving pipeline, allowing responses to be grounded in current, publicly available data without requiring external API calls or custom retrieval logic.

Exam trap

Cisco often tests the distinction between grounding with static knowledge bases (like AWS Bedrock Knowledge Bases) and dynamic, real-time internet search grounding, leading candidates to mistakenly select Azure OpenAI with Bing Search grounding because it also uses a search engine, but the question specifically asks for the platform's unique feature—and Vertex AI's native integration with Google Search is the only one that is built directly into the model serving platform without requiring a separate search service subscription or API key.

How to eliminate wrong answers

Option A is wrong because the Gemini API without grounding does not support any form of internet search grounding; it relies solely on the model's pre-trained knowledge, which is static and cannot incorporate real-time search results. Option C is wrong because Azure OpenAI with Bing Search grounding, while capable of grounding with Bing, is not a unique feature of the Azure platform in this context—the question asks for the platform whose feature uniquely supports the requirement, and Vertex AI's Grounding + Google Search is the only one that is natively built into the model serving infrastructure without requiring a separate search service integration. Option D is wrong because AWS Bedrock with Knowledge Bases is designed for grounding against private, static data sources (e.g., documents, databases) and does not support real-time internet search grounding; it lacks the ability to dynamically query live web content.

Practice this question →

Multi-Selectmedium

A data scientist wants to train a model using BigQuery ML. Which two statements are true about BigQuery ML? (Choose two.)

Select 2 answers

A.It requires a separate Vertex AI training cluster

B.It supports only linear regression models

C.Data must be exported to Cloud Storage before training

D.Models can be trained using SQL directly on BigQuery data

E.It supports both supervised and unsupervised learning

AnswersD, E

BigQuery ML uses SQL for model creation.

Why this answer

BigQuery ML supports supervised and unsupervised algorithms using SQL, and data never needs to leave BigQuery.

Practice this question →

MCQhard

An organization is running a large-scale training job for a custom NLP model with a batch size of 2048 and sequence length of 512. They need to minimize training time while keeping costs predictable. Which Google Cloud hardware should they choose?

A.Cloud TPU v5e pods

B.Compute Engine with NVIDIA A100 GPUs

C.Edge TPU devices

D.Compute Engine with NVIDIA T4 GPUs

AnswerA

TPU v5e pods are optimized for large-scale training, providing high throughput and predictable cost, ideal for large batch sizes and sequence lengths.

Why this answer

Cloud TPU v5e pods are purpose-built for large-scale training of transformer-based NLP models, offering high-throughput matrix multiplication and efficient scaling across multiple chips. With a batch size of 2048 and sequence length of 512, TPU v5e pods deliver superior training speed and predictable pricing via reserved capacity, minimizing time-to-train compared to GPU alternatives.

Exam trap

The trap here is that candidates often default to choosing NVIDIA A100 GPUs due to their general popularity, overlooking that TPU pods are specifically optimized for large-scale transformer training with predictable pricing and superior scaling efficiency.

How to eliminate wrong answers

Option B is wrong because NVIDIA A100 GPUs, while powerful, are general-purpose accelerators that lack the dedicated matrix-multiply units (MXU) and high-bandwidth interconnects of TPU pods, leading to higher cost and slower training for large-batch transformer workloads. Option C is wrong because Edge TPU devices are designed for low-power inference at the edge, not for large-scale training, and cannot handle batch sizes of 2048 or sequence lengths of 512. Option D is wrong because NVIDIA T4 GPUs are mid-range inference and training GPUs with lower memory bandwidth and fewer tensor cores, making them unsuitable for large-batch NLP training and resulting in significantly longer training times.

Practice this question →

MCQeasy

Which Google Cloud service allows you to run machine learning models directly using SQL queries on data in BigQuery?

A.Cloud Functions

B.BigQuery ML

C.Vertex AI

D.Dataflow

AnswerB

BigQuery ML allows SQL-based ML directly in BigQuery.

Why this answer

BigQuery ML enables users to create, train, and deploy ML models using standard SQL, eliminating the need to move data to a separate environment.

Practice this question →

MCQmedium

A company is deploying a custom large language model for internal use and requires the lowest cost for inference while maintaining reasonable quality. They can tolerate slight latency. Which Gemini model variant should they choose?

A.Gemini Ultra

B.Gemini Flash

C.Gemini Nano

D.Gemini Pro

AnswerB

Optimized for lower cost and fast inference with decent quality.

Why this answer

Gemini Flash is designed for low-latency and cost-efficient inference while maintaining strong quality, making it the ideal choice for internal deployments where cost is the primary concern and slight latency is acceptable. It balances performance and expense better than the other variants for this specific requirement.

Exam trap

The trap here is that candidates often assume 'Pro' is always the best cost-quality trade-off, but Google specifically positions Flash as the cost-optimized variant for high-volume, latency-tolerant inference, making it the correct answer when lowest cost is the priority.

How to eliminate wrong answers

Option A is wrong because Gemini Ultra is the largest and most capable model, optimized for maximum quality and complex reasoning, but it incurs the highest inference cost and latency, which contradicts the need for lowest cost. Option C is wrong because Gemini Nano is the smallest model designed for on-device deployment with minimal resource usage, but it sacrifices too much quality and capability for internal enterprise use cases that require reasonable quality. Option D is wrong because Gemini Pro offers a good balance of quality and cost but is more expensive than Flash for inference, as Flash is specifically optimized for faster and cheaper serving while maintaining competitive quality.

Practice this question →

MCQhard

A company is deploying a chatbot using Vertex AI and wants to ensure that the model's responses are grounded in Google Search results to reduce hallucinations. Which feature should they enable?

A.Vertex AI Agent Builder

B.Retrieval-Augmented Generation (RAG) with internal documents

C.Gemini API with custom fine-tuning

D.Vertex AI Search for grounding

AnswerD

Vertex AI provides Google Search grounding to use search results as a knowledge source.

Why this answer

Google Search grounding in Vertex AI allows the model to retrieve real-time information from Google Search to ground answers. RAG uses private data, not web search. Vertex AI Agent Builder includes grounding but is for building agents, not specifically the grounding feature itself.

Practice this question →

MCQmedium

A healthcare organization needs to run ML models on patient data stored in BigQuery while ensuring data never leaves the database. Which service allows them to create and execute ML models directly in BigQuery SQL?

A.Cloud Functions

B.Vertex AI Prediction

C.Vertex AI Workbench

D.BigQuery ML

AnswerD

BigQuery ML allows users to create, train, and evaluate ML models using SQL queries directly on BigQuery data.

Why this answer

BigQuery ML enables SQL-based ML model creation and execution directly on data in BigQuery, meeting the requirement without data movement.

Practice this question →

MCQeasy

Which Google Cloud AI service provides a unified ML platform for building, deploying, and managing ML models in production?

A.AI Platform

B.Vertex AI

C.BigQuery ML

D.Cloud AutoML

AnswerB

Vertex AI is the single platform for all ML activities, including training, deployment, and management.

Why this answer

Vertex AI is the correct answer because it is Google Cloud's unified ML platform that integrates data engineering, data science, and ML engineering workflows into a single service. It provides end-to-end capabilities for building, training, deploying, and managing ML models in production, including AutoML, custom training, model registry, and MLOps features like continuous evaluation and monitoring.

Exam trap

The trap here is that candidates often confuse AI Platform (the legacy service) with Vertex AI, not realizing that Vertex AI is the successor that consolidates all ML capabilities into a single, unified platform, making AI Platform a deprecated option in the context of current Google Cloud ML strategy.

How to eliminate wrong answers

Option A is wrong because AI Platform (now legacy) was the predecessor to Vertex AI; it lacked the unified integration of AutoML and custom training under a single API and did not provide the same level of MLOps tooling, such as model monitoring and feature store. Option C is wrong because BigQuery ML is a service that allows users to create and execute ML models using SQL queries directly in BigQuery, but it is not a unified ML platform for building, deploying, and managing models in production—it is limited to in-database ML and does not support custom training frameworks or production deployment pipelines. Option D is wrong because Cloud AutoML is a subset of Vertex AI that focuses on training high-quality models with minimal effort using Google's transfer learning and neural architecture search, but it does not provide the full platform capabilities for custom model development, deployment, and management that Vertex AI offers.

Practice this question →

MCQeasy

A company wants to build a text-to-speech application for generating voiceovers in multiple languages. They need to use a pre-built Google API without training custom models. Which service should they use?

A.Cloud Text-to-Speech API

B.Vertex AI Text-to-Speech with a custom model

C.Gemini API with a custom prompt

D.Cloud Speech-to-Text API

AnswerA

Cloud Text-to-Speech API provides pre-built voices in many languages, no custom training needed.

Why this answer

Cloud Text-to-Speech API is a pre-built service for converting text to natural-sounding speech in many languages. The other options are either for speech recognition or not pre-built APIs.

Practice this question →

MCQeasy

A healthcare company needs to process medical records (e.g., discharge summaries) to extract structured data. Which AI API is specifically designed for this purpose?

A.Natural Language AI

B.Translation AI

C.Document AI with Healthcare NLP

D.Vision AI

AnswerC

Healthcare AI (via Document AI Healthcare NLP) is specialized for medical records.

Why this answer

Healthcare AI is purpose-built for medical documents, providing features like entity extraction for clinical data.

Practice this question →

MCQmedium

A startup is prototyping a multimodal AI application that processes images and text. They have a limited budget and want the fastest time to market, with minimal infrastructure setup. Which combination of services should they use for prototyping?

A.Vertex AI Prediction and Cloud Storage

B.Google AI Studio (Gemini API) and Colab

C.Cloud Run and Firestore

D.Vertex AI Workbench and BigQuery ML

AnswerB

Google AI Studio offers a free tier for Gemini API, and Colab provides free GPU notebooks — ideal for rapid prototyping with multimodal data.

Why this answer

Option B is correct because Google AI Studio provides immediate access to the Gemini API for multimodal (image+text) processing without any infrastructure setup, and Colab offers a free, managed Jupyter environment with pre-installed libraries for rapid prototyping. This combination minimizes time to market and cost, aligning perfectly with the startup's constraints.

Exam trap

The trap here is that candidates often over-engineer the solution by choosing managed ML platforms like Vertex AI Prediction, forgetting that prototyping prioritizes speed and minimal setup over production-grade scalability.

How to eliminate wrong answers

Option A is wrong because Vertex AI Prediction requires deploying a model to an endpoint, which involves infrastructure setup and ongoing costs, making it slower and more expensive for prototyping. Option C is wrong because Cloud Run and Firestore are serverless compute and database services, not designed for multimodal AI processing; they would require building custom ML logic and lack built-in multimodal capabilities. Option D is wrong because Vertex AI Workbench is a managed notebook environment for model development, and BigQuery ML is for SQL-based ML on tabular data, neither providing direct multimodal AI inference like the Gemini API.

Practice this question →

Multi-Selecthard

A company is deploying a GenAI application that must meet SOC 2 compliance. Which three Google Cloud offerings can be used in a compliant manner? (Choose three.)

Select 3 answers

A.Colab (consumer version)

B.Google AI Studio (free tier)

C.Vertex AI

D.Document AI

E.BigQuery ML

AnswersC, D, E

Vertex AI supports SOC 2 compliance.

Why this answer

Vertex AI is correct because it operates on Google Cloud's infrastructure, which is SOC 2 compliant when configured properly. It provides managed ML services that can be deployed within a VPC-scoped environment, allowing customers to meet data residency, access control, and audit logging requirements mandated by SOC 2.

Exam trap

Cisco often tests the misconception that any free-tier or consumer-grade Google AI tool (like Colab or AI Studio) can be used for compliance, when in fact only enterprise-grade services within a properly configured Google Cloud environment meet SOC 2 requirements.

Practice this question →

Multi-Selectmedium

A developer wants to use Gemini for multimodal tasks involving images and text. Which two features are available via the Gemini API on Vertex AI? (Choose two.)

Select 2 answers

A.Fine-tuning with images

B.Image generation

C.Function calling

D.Code execution

E.Multimodal understanding (image+text)

AnswersC, E

Function calling is supported on Vertex AI.

Why this answer

Gemini on Vertex AI supports multimodal input (image+text) and function calling.

Practice this question →

Multi-Selecthard

A research team wants to leverage Google DeepMind's work to accelerate drug discovery. They are interested in using a model that predicts protein structures and another that can generate novel protein sequences with desired properties. Which TWO Google DeepMind achievements are most relevant? (Select 2 options.)

Select 2 answers

A.WaveNet

B.Gemini

C.AlphaCode

D.AlphaFold

E.AlphaProteo

AnswersD, E

Predicts protein 3D structures, fundamental to drug discovery.

Why this answer

AlphaFold (D) is correct because it is Google DeepMind's breakthrough model for predicting protein 3D structures from amino acid sequences, which directly accelerates drug discovery by enabling researchers to understand target proteins. AlphaProteo (E) is correct because it is DeepMind's AI system designed to generate novel protein sequences that bind to specific targets, effectively creating new proteins with desired therapeutic properties.

Exam trap

Cisco often tests the ability to distinguish between general-purpose AI models (like Gemini or WaveNet) and domain-specific scientific models (like AlphaFold and AlphaProteo), where candidates mistakenly select familiar names without verifying their specific application in drug discovery.

Practice this question →

MCQmedium

A company needs to deploy a chatbot on a mobile device that must work offline. They want to use Gemini for natural language understanding but need minimal latency and no cloud dependency. Which Gemini model variant is most appropriate?

A.Gemini Flash

B.Gemini Nano

C.Gemini Pro

D.Gemini Ultra

AnswerB

Gemini Nano is designed for on-device execution, enabling offline operation.

Why this answer

Gemini Nano is the most appropriate variant because it is specifically designed for on-device deployment, enabling offline operation with minimal latency. It is optimized for mobile devices through quantization and efficient architecture, allowing natural language understanding without any cloud dependency.

Exam trap

The trap here is that candidates often confuse 'lightweight' cloud models like Gemini Flash with truly on-device models like Gemini Nano, assuming that any 'fast' or 'small' model can work offline without understanding the fundamental requirement of local execution.

How to eliminate wrong answers

Option A is wrong because Gemini Flash is a lightweight cloud-based model optimized for speed and cost, but it still requires an internet connection to access Google's servers, making it unsuitable for offline use. Option C is wrong because Gemini Pro is a mid-tier cloud model designed for high-quality responses in cloud environments, not for on-device or offline scenarios. Option D is wrong because Gemini Ultra is the largest and most capable cloud model, intended for complex tasks with cloud infrastructure, and cannot run on a mobile device offline due to its massive computational requirements.

Practice this question →

MCQeasy

Which Google Cloud AI service would you use to transcribe customer service call recordings into text for subsequent analysis?

A.Speech-to-Text

B.Text-to-Speech

C.Translation API

D.Document AI

AnswerA

Speech-to-Text transcribes audio into text.

Why this answer

Speech-to-Text (STT) is the correct service because it is specifically designed to convert audio speech into written text using automatic speech recognition (ASR) models. For customer service call recordings, STT can handle domain-specific vocabulary, multiple speakers, and various audio formats, enabling downstream analysis like sentiment analysis or keyword extraction.

Exam trap

The trap here is confusing Speech-to-Text with Text-to-Speech or assuming that Translation API can handle audio input, when in fact it only works on text, leading candidates to pick a service that does not perform audio transcription.

How to eliminate wrong answers

Option B (Text-to-Speech) is wrong because it converts text into spoken audio, the reverse of what is needed for transcribing recordings. Option C (Translation API) is wrong because it translates text between languages but does not perform speech recognition or transcription from audio. Option D (Document AI) is wrong because it processes scanned documents and PDFs for text extraction and layout analysis, not audio files.

Practice this question →

MCQhard

A regulated industry client requires that all AI model predictions be logged with a traceable audit trail, including the model version, input data, and output, for compliance with internal policies. Which Vertex AI feature should they enable?

A.Vertex AI Explainable AI

B.Vertex AI Model Monitoring (with prediction logging)

C.VPC Service Controls

D.Vertex AI Feature Store

AnswerB

Model Monitoring can log predictions, model version, and input/output for audit trails.

Why this answer

Vertex AI Model Monitoring with prediction logging captures model version, input data, and output for every prediction request, storing them in BigQuery or Cloud Logging to create a traceable audit trail. This directly meets compliance requirements for regulated industries by providing immutable logs that can be queried and audited. Other Vertex AI features like Explainable AI or Feature Store do not offer the same comprehensive logging and version tracking needed for audit trails.

Exam trap

The trap here is that candidates confuse 'Explainable AI' (which explains predictions) with 'logging for audit trails' (which records predictions), or they assume VPC Service Controls handle logging, when in fact they only control network access.

How to eliminate wrong answers

Option A is wrong because Vertex AI Explainable AI provides feature attributions and explanations for model predictions, but it does not log prediction data or model versions for audit trails. Option C is wrong because VPC Service Controls enforce network security boundaries and data exfiltration prevention, but they do not capture or store prediction logs. Option D is wrong because Vertex AI Feature Store manages feature data for training and serving, but it does not log model predictions or versions for compliance auditing.

Practice this question →

MCQhard

An organization wants to ensure that when their employees use the Gemini API via Vertex AI, the grounding searches are restricted to internal company knowledge bases rather than the public web. Which feature should they enable?

A.Enterprise Data Governance on Vertex AI

B.VPC Service Controls

C.Google Search Grounding

D.Vertex AI Search (with private data indexing)

AnswerD

Vertex AI Search can index internal documents and be used as a grounding source for Gemini API calls.

Why this answer

Vertex AI Search allows organizations to index private, internal data sources (e.g., documents, databases) and use them as the grounding source for Gemini API queries. By enabling this feature, grounding searches are restricted to the indexed private knowledge base, ensuring no public web results are used. This directly meets the requirement to keep grounding internal.

Exam trap

The trap here is that candidates may confuse 'Google Search Grounding' (which uses the public web) with the ability to ground on private data, leading them to select Option C instead of recognizing that Vertex AI Search with private data indexing is the correct solution.

How to eliminate wrong answers

Option A is wrong because Enterprise Data Governance on Vertex AI provides data access controls and audit logging, but it does not restrict grounding sources for Gemini API queries. Option B is wrong because VPC Service Controls create a security perimeter around Google Cloud resources, but they do not control the grounding source used by the Gemini API. Option C is wrong because Google Search Grounding explicitly enables grounding via the public web, which is the opposite of the requirement to restrict to internal knowledge bases.

Practice this question →

MCQhard

A regulated healthcare organization needs to use Google Cloud AI services for processing protected health information (PHI). They require a signed Business Associate Agreement (BAA) and HIPAA compliance. Which service provides these assurances?

A.Google AI Studio

B.Colab Enterprise

C.Gemini API directly

D.Vertex AI

AnswerD

Vertex AI can be covered under Google Cloud's HIPAA BAA.

Why this answer

Vertex AI is the correct choice because it is the only Google Cloud AI service that offers a signed Business Associate Agreement (BAA) and is explicitly covered under Google Cloud's HIPAA compliance framework. This allows regulated healthcare organizations to process protected health information (PHI) with the necessary contractual and security assurances.

Exam trap

The trap here is that candidates may assume the Gemini API alone is HIPAA-compliant because it is a Google service, but in reality, only when accessed through Vertex AI (which provides the BAA and enterprise controls) does it meet healthcare regulatory requirements.

How to eliminate wrong answers

Option A is wrong because Google AI Studio is a free, web-based prototyping tool that does not offer a BAA or HIPAA compliance, and it is not designed for production workloads involving PHI. Option B is wrong because Colab Enterprise is a managed notebook environment that, while it can use Google Cloud resources, does not itself provide a BAA or HIPAA compliance for PHI processing. Option C is wrong because the Gemini API directly, when accessed via the standard API endpoint, does not include a BAA or HIPAA compliance; only when used through Vertex AI (which wraps the Gemini API) does the BAA and HIPAA coverage apply.

Practice this question →

MCQmedium

A research team at a university is exploring protein folding predictions. They need access to state-of-the-art models and large-scale computational resources at no cost for academic use. Which Google Cloud offering should they use?

A.Colab notebooks with AlphaFold

B.Google Cloud TPU v5e pods via Cloud TPU API

C.Vertex AI Model Registry with AlphaFold as a pre-trained model

D.BigQuery ML with a custom protein folding model

AnswerA

AlphaFold notebooks are available on Colab, providing free GPU resources for protein folding predictions in an academic setting.

Why this answer

Google DeepMind's AlphaFold provides cutting-edge protein structure predictions. Colab offers free GPU notebooks, and AlphaFold is available as a Colab notebook for academic use.

Practice this question →

MCQeasy

Which Google DeepMind achievement is recognized for predicting protein structures and advancing drug discovery?

A.AlphaFold

B.AlphaGo

C.Gemini

D.AlphaCode

AnswerA

AlphaFold predicts protein 3D structures from amino acid sequences, revolutionizing biology and drug discovery.

Why this answer

AlphaFold is the correct answer because it is a groundbreaking AI system developed by Google DeepMind that predicts the 3D structure of proteins from their amino acid sequences with atomic-level accuracy. This achievement has revolutionized computational biology by solving a 50-year-old grand challenge in molecular biology, enabling significant advances in drug discovery, enzyme design, and understanding disease mechanisms.

Exam trap

Cisco often tests the distinction between domain-specific AI achievements (like AlphaFold for biology) versus general-purpose AI models (like Gemini) or game-playing AI (like AlphaGo), so candidates may confuse the application area of each DeepMind project.

How to eliminate wrong answers

Option B is wrong because AlphaGo is an AI program that mastered the board game Go using deep reinforcement learning and Monte Carlo tree search, not protein structure prediction. Option C is wrong because Gemini is a multimodal large language model family designed for text, image, audio, and video understanding, not for structural biology or drug discovery. Option D is wrong because AlphaCode is an AI system for competitive programming that generates code solutions to algorithmic problems, not for predicting protein structures.

Practice this question →

100

MCQeasy

Which Google service provides free access to Jupyter notebooks with GPU support for prototyping ML models?

A.Colab

B.Kaggle Notebooks

C.Vertex AI Workbench

D.BigQuery Studio

AnswerA

Colab offers free notebooks with GPU support.

Why this answer

Google Colab is a free notebook service with GPU support, commonly used for prototyping.

Practice this question →