designing-gemma.app

A structured framework for evaluating local LLMs using Ollama.

Systematic Evaluation of Local LLMs

designing-gemma provides a standardized methodology for running reproducible experiments on open-source models, focusing on measurable performance and alignment.

Background

Understanding the context: The rise of open models like Gemma 4, the motivation behind community benchmarking (e.g., Dev.to contests), and the need for reproducible evaluation pipelines.

Experiment Design

The core methodology: Structuring experiments with clear run/review cycles, defining evaluation metrics, and establishing voice systems for consistent, objective reporting.

Experiments

The execution layer: A browser interface where users can access and manage structured experiment runs, results, and comparative analyses.

Experiment browser coming soon

%