MicroLLM Lab lets you try 7 tiny LLMs directly in your browser. The focus is on objective checks using regex or exact tokens, not writing quality. A 135M model is allowed to fail — that is the measurement.

Pick models, then run. Speed (tokens/s, sustained decode, suite wall) and accuracy (pass rate on objective tests) are calculated from runs in this browser. Numbers stay on this machine. Charts use the latest suite per model.

Your Name or Handle Device & Hardware Information. Write a benchmark in JavaScript. The editor is eval()’d in this origin, then each check runs on the model’s decoded text. Prompt for a larger LLM Function form.