Case Studies

Real-world production deployments of distilled small language models.

Case Study

Knowunity — 50% LLM Cost Reduction

Replaced frontier model API calls with distilled SLMs, cutting inference costs by 50% without sacrificing quality.

Classification
Read more →
Case Study

Octodet — Customer Study

How Octodet uses distil labs to power their AI workflows.

Classification
Read more →
Case Study

Rocketgraph — Customer Study

Rocketgraph customer study with distil labs.

Question Answering
Read more →
Distil Labs Enables Rocketgraph's Private AI on IBM Power with Small Language Models
Case Study

Distil Labs Enables Rocketgraph's Private AI on IBM Power with Small Language Models

Fine-tuned IBM Granite 3.3 8B for OpenCypher query generation. 85% of Claude 4 performance, 10x faster, 100x less energy. Runs on IBM Power — no data leaves the enterprise.

Question AnsweringOn-Prem / Edge
Read more →
Case Study

Uptime Industries — Custom Model in Days from ~100 Datapoints

Built a custom model from ~100 datapoints in days. Self-service retraining with no vendor dependency.

Question Answering
Read more →