Blog & Demos

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

The pattern we keep seeing in edtech: smaller models, better decisions
Case StudyClassification

The pattern we keep seeing in edtech: smaller models, better decisions

Three education platforms, three narrow high-volume decisions. Fine-tuned small models matched the frontier models they replaced while cutting inference cost 68% in one case, halving false positives in another, and beating the production grader in a third, trained on nothing but existing logs.

Does base-model accuracy predict fine-tuned performance: a mid-size MoE benchmark
BenchmarkClassificationTool CallingQuestion Answering

Does base-model accuracy predict fine-tuned performance: a mid-size MoE benchmark

Across four comparable mid-size MoE models on seven tasks, base-model rank does not predict fine-tuned rank: the lowest-ranking base (NVIDIA Nemotron-3-Nano-30B) gains the most and ties for the best, and once tuned it matches its 550B teacher on most tasks.

Agent Distillation with dltHub: the traces your agents already produce train the smaller model that replaces them
Case StudyAgentic AI

Agent Distillation with dltHub: the traces your agents already produce train the smaller model that replaces them

See what each agent costs, then replace the expensive ones with a hosted drop-in model at 50-90% lower inference cost. Launching with dltHub's standardized ingestion layer, so there is no pipeline to build.

Don't Build a Router. Train the Small Model to Know When to Defer.
GuideTool CallingAgentic AI

Don't Build a Router. Train the Small Model to Know When to Defer.

A fine-tuned small model handles the easy majority of customer-support turns and defers the genuinely-hard minority to a frontier model — matching all-frontier quality at a fraction of the cost. No router, no thresholds, no second classifier: the small model is trained to recognize when it's out of its depth and escalate with a single tool call.

Giving Superpowers to Your LLMs with SLMs
DemoAgentic AITool CallingOn-Prem / Edge

Giving Superpowers to Your LLMs with SLMs

Part 2 of the autonomous bug-fixing agent series: why the intelligent harness keeps the LLM orchestrator general-purpose and offloads domain work to cheap, fine-tuned SLM tools — cutting cost from ~$0.07 to ~$0.001 per incident.

Distil PII Redactor: an OpenClaw Skill
GuideInformation ExtractionOn-Prem / Edge

Distil PII Redactor: an OpenClaw Skill

Locally redact PII from text using a fine-tuned 1B parameter model packaged as an OpenClaw skill. Your sensitive data never leaves your machine.

Autonomous Bug Fixing Agent with distil labs' SLM and Warp Oz
DemoAgentic AIOn-Prem / Edge

Autonomous Bug Fixing Agent with distil labs' SLM and Warp Oz

A self-healing loop that diagnoses production failures with a fine-tuned 0.6B SLM and applies the fix with Warp Oz — closing incidents in seconds, no humans paged.

Train an SLM from your production traces with the distil labs Claude skill
GuideTool CallingAgentic AI

Train an SLM from your production traces with the distil labs Claude skill

A walkthrough of using the distil labs Claude skill to turn 327 noisy production traces into a fine-tuned Qwen3-1.7B multi-turn tool-calling model, deployed on a managed endpoint in a single conversation.

Why training on production traces fails (and what to do instead)
BenchmarkTool CallingAgentic AI

Why training on production traces fails (and what to do instead)

Training directly on production traces doesn't work as well as you'd expect. We tested across five scenarios and synthetic data from traces scores up to 26 percentage points higher in accuracy.