Guides
How-tos and strategic perspectives on building with small language models.
Three ways to put a small model into production
Getting a small model into production comes down to three patterns: handoff, skill, and stage swap. Which one fits is decided by where the repeated narrow work already sits in your system.
Train and deploy a small model in 30 minutes using the CLI or your coding agent
Training a task-specific small model is six stages, starting from the production traces you already collect. A first model takes about 30 minutes, and most of that is jobs running without you. You drive it from the CLI or hand it to your coding agent.
Conversations are now first-class citizens: two new task types for whole-conversation training
Two new task types, chat-completion and chat-completion-agentic, fine-tune small models on complete conversations: text and tool calls together, up to the full agent loop of calling a tool, reading the result, and deciding what to do next.
Gemini 2.5 Flash-Lite retires on a date you don't pick, and a like-for-like swap wastes the migration
Google has announced the retirement of the Gemini 2.5 series, no earlier than October 16, 2026, with the exact date to be set on Google's schedule. Every team running a narrow high-volume job on these models has to re-qualify a replacement whether they want to or not. The default move is another general-purpose workhorse, which means paying to keep the same roughly 80% accuracy on a task that is worth more than that. One education platform spent that same migration on a fine-tuned small model instead and went from 81% to 93% accuracy with inference cost down 68%.
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.
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.
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.
Full-Stack Production Language Models: Expert Model Optimization Meets Scalable GPU Infrastructure
How distil labs and Cerebrium combine expert model optimization with serverless GPU infrastructure to deliver an end-to-end stack for replacing expensive LLM inference with lean, production-grade small-model deployments.
From Production Traces to a Faster, Cheaper, Accurate Model
Learn how to turn your production LLM agent traces into a compact specialist model that outperforms the original, with zero manual annotation and deployment in under 12 hours.