AI & Agent Systems

Local LLM Lab

A measured field guide to every local model installed on Apple Silicon.

Local LLM Lab interface showing the installed-model inventory and measured comparisons.
Local LLM Lab interface showing the installed-model inventory and measured comparisons. Download the editable Excalidraw source.

What it is

Local LLM Lab turns installed local model builds and benchmark evidence into a practical guide: what each build is good at, what it costs to run, and where it beats or loses to the cloud.

Python scripts inspect live Hugging Face, Ollama, MLX and Apple model inventories, join them to checked-in benchmark results, and generate a static React guide with exact model revisions kept separate from runtime behaviour.

Evidence & links

Related reading