About

This tool helps you figure out which open-source LLMs your computer can run locally, and roughly how fast, before you download anything. Everything runs in your browser — no account, no tracking of your hardware, no backend.

Estimates are derived from device specs and model architectures, not live benchmarks. See the methodology for details and limitations.

The model list is refreshed automatically each week from the Hugging Face Hub — params, quantizations, and download sizes stay current without manual updates.

When a model is too large for your machine, we may link to cloud GPU providers that can run it; the build advisor also links to hardware to buy. Some of those are affiliate links — if you sign up or buy through them we may earn a small commission, at no cost to you. It never changes which models or machines we show, or how we rank them — the ranking is always cheapest-that-works first.