Learn
Practical guides to fine-tuning, distillation, and deploying small language models.
Open-Book vs Closed-Book QA
Two ways to make a small model answer questions about your documents: retrieve the passage at query time, or bake the knowledge into the weights. The data, the operations, and the provenance differ sharply.
Open Source vs Proprietary Models for Production
The decision is about control, not quality: who can serve the weights, what the licence permits, where your data travels, and who decides when the model changes underneath you.
Prompt Engineering vs Fine-Tuning
Prompting steers a model's existing behaviour at inference time; fine-tuning changes the weights. What that mechanical difference means for consistency, cost per request, and the ceiling each one hits.
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.