Small Models Quiz
What fits in device memory, why bandwidth sets generation speed, which runtime to use per platform, and how to ship quantised weights with a cloud fallback that keeps the privacy promise.
Small Models Quiz
Test your knowledge of edge AI, small language models (Phi-4, Gemma), quantization, ONNX Runtime, Ollama, Copilot+ PC, and on-device inference.
Apply the decisions to the scenario
Each question tests one decision from Read, not a definition. The explanation names the decision it checks.
1. Which task suits a 3B on-device model?
2. Roughly how much memory do 3 billion parameters need at 4-bit quantisation?
3. The device model is unsure about a note. What is a sensible design?
4. How should a new on-device model version be released?
Continue reading
All LLM Model Landscape articles →GPT: OpenAI's Model Family in Practice
The GPT-6 tiers, what reasoning effort replaced, when to use the Responses API over Chat Completions, how the bill is calculated, and what is different on Azure.
Claude: Anthropic's Model Family in Practice
The four Claude tiers, adaptive thinking and effort, the tool-use rules that differ from other providers, prompt caching, and where you can run it.
Llama: Open-Weight Models for Production
The Llama lineup and licence, serving with Ollama and vLLM, GPU memory sizing, and an honest look at when a hosted API is still the better choice.
Discussion
Sign in to share your feedback and join the discussion.