Learn
Practical guides to fine-tuning, distillation, and deploying small language models.
Q4 vs Q8 vs FP16 for Your SLM
A side-by-side of the three precisions you will actually choose between when serving a distilled model, with the documented bits-per-weight figures, the size arithmetic for real model tiers, and the case for each.
Qwen vs Llama vs Gemma for Tool Calling
Which of the three big open model families you can actually use for tool-calling tasks, what the measured results say about each, and why the family matters less than whether you fine-tuned at all.
Qwen3 1.7B vs Gemma 3 1B for Classification
Head-to-head on the two most common 1B-class students: specs, published fine-tuning ranks, the task-compatibility difference that decides most cases, and which one to train first.
RAG vs Fine-Tuning: Which One Fixes Your Problem?
RAG changes what the model can see; fine-tuning changes what the model does. Side-by-side on mechanism, update cost, and latency, with the measured evidence for each.
Self-Hosted vs Managed Inference
Comparing running your own SLM endpoint against paying someone to run it, across control, cost at volume, operational burden and data residency, with the published per-million-request figures for both sides.
Trace Formats: OpenAI Messages vs Langfuse
A field-by-field comparison of the two trace formats accepted by distil labs, when to pick each, and the two additional observation formats for images and unstructured context.
Traces vs Synthetic Data: Which Trains a Better Model?
Benchmark results comparing a student fine-tuned directly on production traces against one trained on synthetic data generated from the same traces, across five corruption scenarios.
What Does It Cost to Fine-Tune a Small Language Model?
The distil labs free tier covers two full training runs at no cost and credit packs are listed at $1,000 for 10 runs, plus the configuration parameters that actually determine what a run consumes.
What Does It Cost to Run a Small Language Model?
Published distil labs figures put a fine-tuned student at roughly $3 per million requests on one H100. Here's what that covers, how it was measured, and which assumptions move it.