What is a local LLM?
Follow a prompt from your keyboard to the model and back. Learn what stays on your machine and what to check.
Learning path
Foundations
Learn how language models and other AI systems work, what “local” changes, and how to choose a model your computer can handle.
Models and hardware
5 lessonsTokens and context windows
See what the model reads, how much it can use at once, and why a long chat can lose earlier details.
Hardware and quantization
Estimate the space weights need, leave room for context, and pick a sensible model size for your machine.
How to choose a model
Read model cards and choose a compatible model based on your task, hardware, and license.
Choose the right kind of AI for a task
Distinguish rules, classifiers, embeddings, and generative models by what they return and how you can check it.
How models work
4 lessonsHow chat templates turn messages into tokens
Trace system, user, and assistant messages through a model’s chat template and diagnose a common formatting problem.
What attention does inside a language model
Work through a tiny attention calculation and connect the result to causal masking, attention heads, and the KV cache.
Read dense, mixture-of-experts, and distilled model cards
Distinguish stored weights, active computation, and training methods before deciding whether a model will fit.
Train a tiny next-token model from counts
Count token pairs, turn them into probabilities, sample a sentence, and score predictions on text the model never saw.