Most apps that run AI on your own computer ship the same one-size-fits-all settings for every chip. Magnitude is a free, open source engine that, when you download a model, spends up to a minute trying different ways to split up the math on your actual chip, then keeps the fastest combination that doesn't change the model's output.
Here is what you get, how to install it, and the catch.
What you get
- On a Mac mini with M4 Pro, replies came 2.19x faster than Ollama on average across 11 popular open models, and prompts were read 1.32x faster.
- On NVIDIA hardware (a DGX Spark), replies came 2.17x faster on average.
- It runs on Apple Silicon, NVIDIA, AMD, Intel, or just a CPU, on macOS, Linux and Windows.
- It's private: prompts, files and models stay on your machine, with no token costs.
- One click connects it to coding agents, Claude Code included, and anything else works through its OpenAI-compatible API.
Free, for your email
Get the full setup steps + the copy-paste setup prompt
The rest of this guide (3 more sections) opens right here. The setup prompt, one paste into Claude that sets it all up, comes by email only. Use your real address.
Unlocks: Install it · The catch · Sources
50,000+ follow where these guides come from. No spam, reply “unsubscribe” any time.
