Thanks. BTW:

- the model I used was gpt4-x-vicuna-13B.ggml.q5_1.bin

- I used 'time' to measure the wall clock time of each command.

- My prompt was:

  Below is an instruction that describes a task. Write a response that appropriately completes the request.
  ### Instruction:
  Write a long blog post with 5 sections, about the pros and cons of emphasising procedural fluency over conceptual understanding, in high school math education.
  ### Response: