# Ollama Model Tester

A dependency-free command-line tool that runs the same prompt against locally installed Ollama models, repeats it a chosen number of times, and saves every response to disk for comparison.

Ollama Model Tester is a small Python script that only uses the standard library, with no separate installation step. It asks interactively which installed Ollama model to use, the prompt text, how many times to run it, a temperature and whether to stream responses live, or all of these can be supplied as command-line flags for scripted use.

Results are grouped into one folder per prompt, named from the prompt's first words plus a hash of its full text, so running the same prompt against a different model drops its output into the same folder for easy comparison. Each model's output file records every run's response together with Ollama's own run metadata such as token counts and timing.

Website: https://github.com/ulyssestenn/omt