Going local
Everything needed to stop paying for an API: hardware maths, the install, and the two tools worth knowing.
- Local setupLlama
Running your first local model
Ollama on a normal laptop, from install to a model answering in about ten minutes, plus how to work out which size actually fits before you download…
Do this first, the rest makes no sense otherwise.
Tested on Llama 3.2 8B · May 2026
Ollama
The simplest way to get a local model answering on your own machine. One command to install, one to pull a model, and an API on localhost that most…
The tool most people settle on.
Tested on Llama 3.3 70B · May 2026
LM Studio
A desktop app for downloading, running and comparing local models without a terminal. Best tool for deciding which quantisation is good enough before…
Use it to pick a quantisation, then go back to Ollama.
Tested on Llama 3.2 8B · May 2026