Your question is INT8 and INT4 Quantization Tradeoffs. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
You are preparing a neural network for lower cost inference and smaller memory footprint, and you need to choose between different quantization schemes.
Explain quantization (INT8, INT4) and its trade-offs.