Local Reasoning Model Token Cost — thinking ON/OFF Measured
I ran 13 questions on gemma4:12b with thinking ON and OFF. Reasoning got one more right while spending 68x the output tokens and 19x the wall-clock.
Tags
LLMEvaluation
2 posts
Local LLM Reproducibility: Testing Temperature and Seed
I sent the same prompt to local Gemma 4 dozens of times. temperature=0 was deterministic, and even at higher temperature a fixed seed collapsed output to one line.