AI-900 Practice Question: Describe features of generative AI workloads on Azure
What is the 'phi' family of models in Azure AI and what makes them distinctive?
⚠ Common exam trap
Test-takers frequently confuse 'small language models' with 'multimodal' or 'specialized' models, assuming that compact size implies limited capability, when in fact the phi family is designed for strong reasoning at a fraction of the resource cost.
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
✓
Small language models from Microsoft Research that achieve strong reasoning performance at compact size
The 'phi' family of models are small language models (SLMs) developed by Microsoft Research that achieve strong reasoning and language understanding performance despite their compact size. They are designed to run efficiently on resource-constrained devices, making them distinctive for edge and offline scenarios where large models are impractical.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Large multimodal models that process images, audio, and text simultaneously
Why it's wrong here
Phi models are decoder-only language models trained on text; they do not natively accept image or audio inputs. Their architecture is optimized for autoregressive text generation, not multimodal fusion. Multimodal systems like GPT-4V require vision encoders and cross-attention blocks, which are absent in Phi's design.
- ✓
Small language models from Microsoft Research that achieve strong reasoning performance at compact size
Why this is correct
The Phi family includes small language models (SLMs) such as Phi-2 and Phi-3, ranging from roughly 1.3 billion to 14 billion parameters. They are trained on high-quality, textbook-like data and demonstrate reasoning performance that often rivals much larger models. This compact size makes them suitable for cost-sensitive, edge, and low-latency deployments.
- ✗
Models specialized exclusively for mathematical calculations
Why it's wrong here
Phi models are general-purpose language models trained on a diverse mixture of web text, code, and synthetic reasoning data, not exclusively mathematical content. They excel at tasks like GSM8K arithmetic and MATH benchmarks, yet they also handle instruction following, summarization, and free-form text generation. Their mathematical ability emerges from pattern learning, not from a specialized symbolic computation engine.
- ✗
A family of image generation models for creative AI tasks
Why it's wrong here
Phi models are text-only small language models that generate tokens via next-token prediction; they contain no diffusion decoder or image synthesis capability. Image generation in Azure AI is handled by separate models like DALL-E, which employ diffusion processes and text-image alignment. Phi's objective is purely textual, so it cannot produce images for creative tasks.
Go deeper
Related to this question
About these practice questions
One of 985 original AI-900 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 AI-900 practice question is part of Courseiva's free Microsoft 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 AI-900 exam.