← Back to projects
AI project

Local Model Lab

A personal lab for exercising local models on realistic tasks. Comparison-first: every run is logged, diffable, and exportable.

Overview

Local Model Lab is a sandbox for running local LLMs alongside retrieval pipelines, then comparing outputs against a benchmark set — all on-device.

Challenge

Local model workflows are easy to spin up but hard to trust. There is no shared harness for "did this actually get better?" that works offline.

Approach

  • Fixed evaluation harness with deterministic seeds.
  • One-click switching between local and cloud models.
  • Record every run with inputs, outputs, and grading rubric.