Learn
Practical guides to fine-tuning, distillation, and deploying small language models.
How Long Does Fine-Tuning Take?
Published distil labs runs land between roughly six and twelve hours end to end. Here is what those figures cover, which stage eats the clock, and what moves it.
How Many Examples Do You Actually Need to Fine-Tune a Model?
Twenty labelled examples is the documented floor and 20 to 100 the usual range. Here are the published results behind those figures and what moves the number in either direction.
How Much Can You Save Replacing an LLM API?
Knowunity cut inference cost by roughly 68% on selected tasks while accuracy rose from 81% to 93%. Here's that measurement, the wider range published alongside it, and what puts you at either end.
How Much Traffic Do You Need Before Traces Are Useful?
There's no published traffic threshold for trace-based training. This works out what the documented processing pipeline (dedup, seed splitting, relevance filtering, relabelling) implies about volume instead.
How Much VRAM Does a 1B, 3B or 8B Model Need?
Working forwards from a chosen model size to the card that can serve it, including the KV cache term computed from published attention configs, the part that decides whether a model that loads will still run at your context length.
How We Benchmarked 12 Small Language Models
The design and results of the distil labs study that fine-tuned 12 small language models on 8 tasks: average ranks, tunability, the student-versus-teacher table, and what the method does and does not establish.
LoRA vs QLoRA: Which Should You Use?
QLoRA is LoRA with the frozen base model quantised to 4 bits. Here is what that buys you, what it costs, and which one to enable for a small student model.
Model Routing vs a Single Specialised Model
A router is a separate component that decides which model handles a request. The alternative is training the decision into the small model itself. Here's what each costs to own.
On-Device LLM Inference in 2026
Published throughput, footprint and accuracy figures for language models running on phones, embedded modules and commodity CPUs, each reported with the hardware and model it was measured on rather than as a general claim.