Open source inference engine that tunes its kernels on your hardware to find the fastest way to run each model. 2x faster than Ollama. Works on Apple Silicon, NVIDIA, AMD, or just a CPU.
Magnitude is an open-source inference server, meaning software that runs language models and answers requests on a user's own computer. It profiles available hardware, recommends suitable local models, and connects them to coding agents for private and offline use on macOS, Linux, or Windows through WSL. Its catalogue entries help agents set up and use Magnitude.
Latest release @magnitudedev/[email protected] · 20 Oct 2026
2 files for Codex, OpenCode and Claude Code: magnitude AGENTS.md, magnitude CLAUDE.md — 2,276 tokens loaded in every session.
AGENTS.md A 2,273 tok CLAUDE.md A 3 tok These files are magnitudedev/magnitude's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.