Quick Answer
The answer is model size and maximum sequence length. These two factors most significantly influence the computational cost of fine-tuning because model size directly determines the total number of parameters and thus the FLOPs and memory required for each forward and backward pass, while sequence length dictates the memory footprint of attention matrices and the compute per training step. On the Oracle Cloud Infrastructure Generative AI Professional 1Z0-1127 exam, this question tests your understanding that per-step cost is dominated by these architectural choices, not by throughput variables like batch size or by dataset size, which only affects total steps. A common trap is confusing batch size with fundamental cost per token—batch size scales throughput but does not change the cost per individual token. Remember the mnemonic “Size and Span” to recall that model size and sequence span are the two primary cost drivers during fine-tuning.
This 1Z0-1127 practice question tests your understanding of fundamentals of large language models. Read the scenario carefully and evaluate each option against the stated constraints before committing to an answer. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
Which TWO factors most significantly influence the computational cost of fine-tuning a large language model?
Batch size
Why wrong: Batch size affects memory but not per-token compute cost.
Number of model parameters
More parameters increase compute and memory requirements.
Maximum sequence length
Longer sequences increase attention computation and memory usage.
Quantization bits
Why wrong: Quantization reduces cost, not increases.
Dataset size
Why wrong: Dataset size affects total training time but not per-step cost.
Answer choices
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
Number of model parameters
Model size (parameters) directly determines FLOPs and memory. Training sequence length affects memory and compute per step. Option C is wrong because batch size affects throughput but not fundamental cost per token. Option D is wrong because quantization usually reduces cost. Option E is wrong because dataset size affects total steps but per-step cost is dominated by model size and sequence length.
Key principle: NAT direction and interface roles matter as much as the IP address mapping. Inside/outside designation controls which traffic is translated.
Answer analysis
For each option: why learners choose it and why it is or isn't the right answer here.
Batch size
Why it's wrong here
Batch size affects memory but not per-token compute cost.
Number of model parameters
Why this is correct
More parameters increase compute and memory requirements.
Related concept
Static NAT maps one inside address to one outside address.
Maximum sequence length
Why this is correct
Longer sequences increase attention computation and memory usage.
Related concept
Static NAT maps one inside address to one outside address.
Quantization bits
Why it's wrong here
Quantization reduces cost, not increases.
Dataset size
Why it's wrong here
Dataset size affects total training time but not per-step cost.
Common exam traps
NAT is not only about the public address. The inside/outside interface roles and the ACL or rule that matches traffic are just as important.
Detailed technical explanation
NAT questions usually test address translation, overload/PAT behaviour, static mappings and whether the right traffic is being translated. Read the interface direction and address terms carefully.
Key takeaway
NAT direction and interface roles matter as much as the IP address mapping. Inside/outside designation controls which traffic is translated.
Real-world example
A small business has 20 workstations on the 192.168.1.0/24 network and one public IP from its ISP. The router uses PAT (NAT overload) so all 20 devices share one public address using different source ports. NAT questions test whether you understand the four address terms and which direction each translation applies.
What to study next
Review the four NAT address types (inside local, inside global, outside local, outside global), PAT port overload, and static vs dynamic NAT use cases. Then practise related 1Z0-1127 NAT questions on configuration and troubleshooting.
Fundamentals of Large Language Models — study guide chapter
Learn the concepts, then practise the questions
Fundamentals of Large Language Models practice questions
Targeted practice on this topic area only
All 1Z0-1127 questions
500 questions across all exam domains
Oracle Cloud Infrastructure Generative AI Professional 1Z0-1127 study guide
Full concept coverage aligned to exam objectives
1Z0-1127 practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Practise 1Z0-1127 questions linked to Fundamentals of Large Language Models.
Practise 1Z0-1127 questions linked to Using OCI Generative AI Service.
Practise 1Z0-1127 questions linked to Building LLM Applications with RAG and Vector Search.
Practise 1Z0-1127 questions linked to Deploying and Managing Generative AI on OCI.
Practise 1Z0-1127 questions linked to 1Z0-1127 fundamentals.
Practise 1Z0-1127 questions linked to 1Z0-1127 scenario.
Practise 1Z0-1127 questions linked to 1Z0-1127 troubleshooting.
Practice this exam
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Fundamentals of Large Language Models — This question tests Fundamentals of Large Language Models — Static NAT maps one inside address to one outside address..
The correct answer is: Number of model parameters — Model size (parameters) directly determines FLOPs and memory. Training sequence length affects memory and compute per step. Option C is wrong because batch size affects throughput but not fundamental cost per token. Option D is wrong because quantization usually reduces cost. Option E is wrong because dataset size affects total steps but per-step cost is dominated by model size and sequence length.
Review the four NAT address types (inside local, inside global, outside local, outside global), PAT port overload, and static vs dynamic NAT use cases. Then practise related 1Z0-1127 NAT questions on configuration and troubleshooting.
Static NAT maps one inside address to one outside address.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Last reviewed: Jun 22, 2026
This 1Z0-1127 practice question is part of Courseiva's free Oracle certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the 1Z0-1127 exam.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.