PMLE Scaling Prototypes into ML Models Practice Question

Your team is deploying a large model on edge devices and needs to reduce its size by 80% while maintaining reasonable accuracy. Which THREE techniques should they consider? (Choose 3.)

⚠ Common exam trap

Google Cloud often tests the misconception that transfer learning reduces model size, when in fact it only transfers learned features and does not compress the model; candidates may confuse it with knowledge distillation.

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

✓

Quantisation to INT8

Quantisation to INT8 reduces the precision of model weights and activations from 32-bit floating point to 8-bit integers, cutting memory usage by approximately 75% (4x compression). This directly addresses the 80% size reduction target while often preserving accuracy within 1-2% through careful calibration and scaling, making it a primary technique for edge deployment.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✓
Quantisation to INT8
Why this is correct
Reduces model size by reducing precision of weights.
✗
Transfer learning from a larger model
Why it's wrong here
Transfer learning does not reduce model size; it may retain the same architecture.
✓
Knowledge distillation
Why this is correct
Trains a smaller student model to mimic larger teacher, reducing size significantly.
✗
Increasing model capacity with more layers
Why it's wrong here
Opposite of compression.
✓
Pruning of redundant connections
Why this is correct
Removes weights that contribute little, reducing storage.

Go deeper

PMLE Scaling Prototypes into ML Models Practice Question

Why each option matters

Option-by-option breakdown

Related to this question