An empirical study of small-model coding agents on a 4 GB RTX 3050: edit format, model choice, retry, decomposition, role-split, and a custom text tool-call loop, measured across ~900 automated trials.

We stopped theorizing and ran ~900 trials on a 4 GB laptop GPU to measure what makes a small local model a good coding agent. The result overturns intuition: the edit format and the editor model decide almost everything, the clever agentic scaffolding mostly hurts, and the simplest setup won.

Tag: Experiment

Tag: Experiment

The 4 GB Experiment: What Actually Makes a Small Model a Good Coding Agent