Module 1 knowledge check · Local models and inference engineering

1. What does local inference guarantee about all connected tools?Nothing by itself; their data flows need separate checkingThey are automatically offlineThey cannot write logs

2. What does the simple parameter-times-bits estimate describe?Guaranteed response speedApproximate weight storage before overheadGuaranteed total device memory use

3. A KV cache is best understood as what?A permanent collection of verified factsA replacement for the model weightsReusable inference state for previously processed tokens

4. Which statement is justified by the example?B completes sooner but A begins responding soonerB is better for every use caseA has higher throughput because it starts sooner

5. What must be checked after an adapter improves formatting?Nothing if training completed successfullyWhether other required behaviours have deterioratedOnly whether the file is smaller than the base model