Blog & Demos
Tutorials, case studies, benchmarks, and open-source demos — everything you need to build with small language models.
GitAra: How We Trained a 3B Function-Calling Git Agent for Local Use
A 3B function-calling model that turns plain English into git commands. Matches the 120B teacher at 92% accuracy — 25x smaller, runs locally via Ollama.
Vibe-Tuning: The Art of Fine-Tuning Small Language Models with a Prompt
From prompt to production-ready model — no datasets, no ML expertise, no GPUs. Automates data generation, distillation, and evaluation.
Benchmarking the Platform
Distilled students match or exceed the teacher LLM on 8 of 10 datasets across classification, NER, open-book QA, tool calling, and closed-book QA.
Small Expert Agents From 10 Examples
How the distil labs platform turns a prompt and a few dozen examples into a small, accurate expert agent — 50-400x smaller than LLMs.
Small Models, Big Wins: Using Custom SLMs in Agentic AI
Agentic systems don't need an LLM everywhere. When to use SLMs vs LLMs, common use cases, and the decision framework.