# Distill Labs Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/distill-labs
> Markdown URL: https://aitinkerers.org/technologies/distill-labs.md
> Technology record last updated: 2026-03-14T07:48:15Z
> Generated: 2026-09-21T15:39:19Z

The developer platform for building task-specific Small Language Models (SLMs): achieve LLM-level accuracy in hours with minimal data via knowledge distillation.

Distil Labs is the developer platform for deploying custom Small Language Models (SLMs) fast. We automate the entire ML pipeline, using knowledge distillation to fine-tune a compact SLM with just a prompt and a few dozen examples (no manual labeling required). This process delivers state-of-the-art accuracy, with models up to 400x smaller than their teacher LLMs. For example, our 1B PII redaction model achieved 0.81 $\pm$ 0.02, effectively matching a 600B+ class LLM like DeepSeek 3.1. Ship your custom model in under eight hours for private, on-device deployment across use cases like text classification, Open Book QA, and structured data extraction.

- Official technology site: https://distillabs.ai
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Teaching small language models a thing or two](https://amsterdam.aitinkerers.org/talks/rsvp_5y9_LDXh3rQ)

I will be presenting our efforts in finetuning a range of small language models (SLMs) for both fun and useful use-cases. I shall go through the pipeline of how to finetune SLMs with limited data and why this might be the future.

- Event context: AI Tinkerers Amsterdam – November 2025 Edition — 2025-11-11 — Amsterdam
- Public talk page: https://amsterdam.aitinkerers.org/talks/rsvp_5y9_LDXh3rQ

## Related Technologies

- [Hugging Face](https://aitinkerers.org/technologies/hugging-face) ([Markdown](https://aitinkerers.org/technologies/hugging-face.md)) — 41 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [Transformers](https://aitinkerers.org/technologies/transformers) ([Markdown](https://aitinkerers.org/technologies/transformers.md)) — 148 public demos