Learn

Practical guides to fine-tuning, distillation, and deploying small language models.

Best Small Language Model for Fine-Tuning in 2025: Qwen vs Llama vs Gemma

A head-to-head comparison of Qwen 3, Llama 3.2, and Gemma 3 for fine-tuning across classification, QA, NER, and tool-calling tasks — with benchmark data to back every claim.

Distillation vs Fine-Tuning: What's the Difference?

Knowledge distillation and fine-tuning are related but distinct techniques. Learn how they differ, when to use each, and how combining them produces the best results for production AI.

Distillation vs Quantization: Which Shrinks Your Model Better?

Distillation and quantization both reduce model size, but they work in fundamentally different ways. Learn the trade-offs and when to use each approach — or combine them.

LoRA vs Full Fine-Tuning: When to Use What

Compare LoRA and full fine-tuning for small language models. Learn the trade-offs in accuracy, speed, and memory so you can pick the right approach for your project.

Deploy an SLM with Ollama

Loading a fine-tuned small language model into Ollama from a local GGUF or straight from Hugging Face, writing a Modelfile that preserves the training-time system prompt, and the chat-template trap specific to this runtime.

Deploy an SLM with vLLM

Serving a distilled small language model on a GPU with vLLM — environment setup, the tool-calling parser flags, querying the OpenAI-compatible endpoint, and the throughput and memory figures we measured on a single H100.

Fine-Tune a Model With 20 Examples

The minimal-dataset route end to end: four files, twenty labelled examples, and the distil CLI commands that turn them into a trained small language model.

How to Choose a Teacher Model for Distillation

Choose a teacher on measured accuracy for your own task, not parameter count. Criteria table, tool-calling constraints, and the teacher evaluation step that settles it.

How to Deploy a Fine-Tuned Small Language Model

The four ways to put a trained SLM into service — managed endpoint, local llama.cpp, self-hosted vLLM, and an offline download — with the constraint that selects each one and the mistakes that quietly break accuracy.