Local or nothing

Local or nothing syllabus

The honest version of "just run it locally" — what fits, what it costs, and the point where it stops being worth it.

Module 0 — What actually fits

Before anything else: whether your hardware is in the game at all. Free, and it should be.

  1. Reading a model card for what it doesn't say — Parameter counts are marketing. Memory at your context length is the constraint. (1 min)
  2. VRAM arithmetic you can do in your head — Weights, KV cache, overhead — and which one surprises you. (2 min)

Module 1 — Quantisation without the folklore

Everyone repeats that 4-bit is fine. Measure it on your task instead.

  1. What quantisation costs you, measured — Not perplexity. Your harness, your probes, one run per format. (1 min, paid)
  2. Picking a format for your hardware — The right answer differs on Apple silicon, on a consumer GPU, and on a server card. (1 min, paid)

Module 2 — The cost model

Where local stops being cheaper, stated as a break-even you can defend.

  1. Tokens, watts and wall-clock — A machine that runs all day has an electricity bill and a depreciation schedule. (1 min, paid)