Blog & Demos

Tutorials, case studies, benchmarks, and open-source demos – everything you need to build with small language models.

distil-expenses: Local Personal Expense Summaries with SLMs
DemoTool CallingQuestion AnsweringOn-Prem / Edge

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.

distil NPC: Small Language Models for Video Game Characters
DemoQuestion AnsweringOn-Prem / Edge

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.

distil-PII: Family of PII Redaction SLMs
GuideInformation ExtractionOn-Prem / Edge

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.

distil labs: Benchmarking the Platform
BenchmarkClassificationQuestion AnsweringTool CallingInformation Extraction

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.

distil labs: Small Models, Big Wins – Using SLMs in Agentic AI
GuideClassificationQuestion AnsweringTool CallingInformation ExtractionOn-Prem / EdgeAgentic AI

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.

distil labs: Small Expert Agents from 10 Examples
GuideClassificationInformation Extraction

distil labs: Small Expert Agents from 10 Examples

An overview of how distil labs turns a prompt and a few dozen examples into a small, accurate expert agent that matches LLM-level results with models 50-400x smaller.