Slm Evaluation Dashboard

Overview

A small language model (SLM) evaluation dashboard that runs entirely offline using Ollama as the local inference backend. It benchmarks multiple small models (2–5B parameters) across three phases: raw inference performance, structured output validation, and temperature variance analysis. Open-source project by Nazgul Sagatova, published on GitHub.

Highlights

• Primary language: Python
• Open source — view the code and contribute on GitHub

Built with

• Python