Local setup
Running models on your own hardware: Ollama, LM Studio, quantisation, and how much memory a given model really needs. No API bill.
- Llama
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…
Tested on Llama 3.2 8B · May 2026