Blog & Demos
Tutorials, case studies, benchmarks, and open-source demos – everything you need to build with small language models.
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.
Fine-Tuning Liquid's LFM2.5: Accurate Tool Calling at 350M Parameters
Liquid AI's LFM2.5-350M reaches 96-98% tool call equivalence after fine-tuning with distil labs across three benchmarks, matching or exceeding a 120B teacher model while staying at 350M parameters.
What Small Language Model Is Best for Fine-Tuning
We benchmarked 15 small language models across 9 tasks to find the best base model for fine-tuning. Qwen3-8B ranks #1 overall. Liquid AI's LFM2 family is the most tunable. Fine-tuned Qwen3-4B matches a 120B+ teacher on 8 of 9 benchmarks.
A 0.6B model outperformed a 120B LLM by 29 points - using dlt, distil labs, and Hugging Face
How to turn production LLM traces into a deployed specialist model using dlt for trace extraction and distil labs for training, achieving 79% exact match with a 0.6B model that beats a 120B teacher by 29 points.
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.
The 10x Inference Tax You Don't Have to Pay
Benchmarking fine-tuned small language models (0.6B-8B) against 10 frontier LLMs across 8 datasets shows that task-specific SLMs match or beat frontier models at 10-100x lower inference cost.
How Knowunity used distil labs to cut their LLM bill by 68%
Knowunity, an edtech startup processing hundreds of millions of AI requests monthly, used distil labs to train a custom small language model that cut inference costs by 68% while improving classification accuracy from 81% to 93%.
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.
How to label your emails locally with a distil labs fine-tuned model and n8n
Build a fully local Gmail email classification pipeline using a distil labs fine-tuned 0.6B model and n8n, keeping all email data private on your machine.