Back to directory

Magnitude

An open-source inference engine that profiles a user's own hardware, recommends the best open models for it, and tunes them for that exact machine, running on Apple Silicon, NVIDIA, AMD or CPU-only setups.

Magnitude

Magnitude is a desktop app that estimates tokens-per-second for every model in its catalog before download, ranking them by speed, accuracy, intelligence and memory, then downloads, tunes (including speculative decoding) and runs the chosen model. The desktop app bundles the magnitude CLI, so no separate install is needed.

One click connects an existing agent such as Pi, OpenCode or Hermes to it. Models load on request and unload when idle or when memory fills, no token costs, API keys or rate limits apply, and models, prompts and files stay on the machine.

It is written in TypeScript, downloads for macOS, Windows and Linux, and is licensed under Apache-2.0.

More in Inference

See all 770
  • OpenDecision

    deepanwadhwa.github.io

    An open-source Python package that answers typed questions about application state or documents using a local natural-language-inference model, returning structured choice, score, yes/no or evidence-relation values instead of free text.

  • Lifeboat

    iterate.ai

    A local inference server that puts an OpenAI- and Anthropic-compatible API in front of open-weight language models running on hardware you control, from a laptop to a GPU cluster.

  • Claude S40

    github.com

    An unofficial Claude chat client for 2007-era Nokia Series 40 phones, built as a Java ME app plus a small Go relay server, with web search, reading mode and saved chats.