LLM Fundamentals →hardMultiple SelectObjective-mapped

1Z0-1127-25 LLM Fundamentals Practice Question

An OCI user wants to reduce the cost of running a generative AI model while maintaining output quality. Which THREE strategies can help achieve this?

⚠ Common exam trap

The 1Z0-1127 exam often tests the misconception that greedy decoding reduces cost (it does not—it only changes the decoding strategy, not the model size or token count) and that increasing max tokens improves quality (it actually increases cost and can degrade output by encouraging rambling).

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

✓

Use a smaller model from the same family

Using a smaller model from the same family (e.g., switching from Llama 3 70B to Llama 3 8B) reduces the number of parameters and computational resources required per inference, directly lowering cost. Smaller models often retain strong performance on many tasks, especially when the task complexity does not demand the full capacity of the larger model, thus maintaining output quality while reducing token processing costs.

Answer analysis

Option-by-option breakdown

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

✗
Use greedy decoding instead of sampling
Why it's wrong here
Greedy decoding does not reduce cost significantly.
✓
Use a smaller model from the same family
Why this is correct
Smaller models are cheaper to run.
✗
Increase max tokens to ensure complete answers
Why it's wrong here
More tokens increase cost.
✓
Implement caching for repeated queries
Why this is correct
Caching avoids redundant computation.
✓
Optimize prompts to be more concise
Why this is correct
Shorter prompts reduce token usage.

Go deeper

1Z0-1127-25 LLM Fundamentals Practice Question

Why each option matters

Option-by-option breakdown

Related to this question