Local Model Family: Llama

Llama is a useful local-model lesson because it makes one trade-off visible: learning the local-model ecosystem, testing fine-tunes, running llama.cpp, and comparing base versus instruct behavior. The point is not to crown a permanent winner. The point is to learn how to match a model family to hardware, task, license, and risk.

Current source signal

Build the small version

Have students pick one Llama base, one instruct variant, and one fine-tune, then explain how they differ.

1. 1Pick one exact model file or runtime tag from the current model card.
2. 2Run three short prompts: one easy, one task-specific, and one likely failure case.
3. 3Record load time, response speed, memory pressure, answer quality, and one surprising failure.
4. 4Write a one-paragraph recommendation: use it, do not use it, or use it only for a narrow job.

llama_family_tree:
  base_model: learns general language patterns
  instruct_model: follows chat instructions
  fine_tune: adapted to a style, task, or policy
  quantized_file: compressed for local runtime

question: which layer changed, and why?

The big idea: remember family tree. Local model work is product design under constraints, not just downloading the model with the loudest leaderboard score.