Research, field notes and results

Case studies, benchmarks, demos and guides from the team building the model factory.

Demo7 Dec 2025

Gitara: How we trained a 3B Function-Calling Git Agent for Local Use

We fine-tuned a small, tool-calling language model to turn plain-English questions into git commands with the accuracy of a cloud LLM.

Demo3 Dec 2025

Resume Roaster AI: Brutally Honest Resume Critique with a Local SLM

A fine-tuned Llama-3.2-3B model that generates sarcastic resume critiques and professional improvement suggestions. Runs entirely locally to keep your personal data private.

Demo17 Nov 2025

distil-commit-bot: AI-Powered Commit Messages for TypeScript

A fine-tuned 0.6B parameter SLM that generates commit messages for TypeScript codebases. Runs locally via Ollama, achieving 90% accuracy compared to a 120B teacher model, at 200x smaller size.

Demo14 Nov 2025

distil-localdoc.py: Automatic Python Documentation Generation

A fine-tuned Qwen3 0.6B model that generates complete, properly formatted Google-style docstrings for your Python code. Runs locally to keep your proprietary code secure.

Demo30 Oct 2025

distil-expenses: Local Personal Expense Summaries with SLMs

Fine-tuned Llama 3.2 models (1B and 3B) for personal expense analysis. Runs locally via Ollama. Query your spending data with natural language while keeping your financial data completely private.

Demo23 Oct 2025

distil NPC: Small Language Models for Video Game Characters

A family of small language models specialized for conversational NPCs in video games. Enables natural language interaction with game characters running entirely on-device, no network required.

Guide21 Oct 2025

distil-PII: Family of PII Redaction SLMs

We trained and released a family of small language models specialized for policy-aware PII redaction that dramatically outperform their pre-trained counterparts.

Benchmark16 Oct 2025

distil labs: Benchmarking the Platform

Benchmarking distil labs' distillation pipeline across classification, information extraction, QA, and tool-calling tasks, showing that compact SLMs consistently match or exceed teacher LLMs.

Guide16 Oct 2025

distil labs: Small Models, Big Wins – Using SLMs in Agentic AI

How small language models can match or beat much larger LLMs when fine-tuned to well-scoped tasks, enabling faster, cheaper, and more private agentic AI workflows.