Magnitude: Releases and Overview
Open-source inference engine written in Rust (Apache-2.0) that compiles and tunes its kernels on the device it runs on. The project reports up to 2x faster than llama.cpp on Metal and CUDA; in our CPU-only measurement it was about 21x slower.
Category: Inference engines and runtimes. Part of our engine and tool tracker.
At a Glance
| Item | Value |
|---|---|
| Repository | magnitudedev/magnitude |
| Latest release | @magnitudedev/cli@0.2.4 (2026-10-02) |
| Install / docs | official documentation |
Release History
Compiled by Local Model Watch from the project’s GitHub releases. Pre-releases are omitted. Where we wrote an article about a release, it is linked in the last column; smaller releases are tracked here only.
| Version | Released | Release notes | Our article |
|---|---|---|---|
| @magnitudedev/cli@0.2.4 | 2026-10-02 | GitHub | Magnitude 0.2.4 Released: Faster Inference and Lower Memory |
| @magnitudedev/cli@0.2.3 | 2026-10-01 | GitHub | — |
| @magnitudedev/cli@0.2.2 | 2026-10-01 | GitHub | — |
Articles on Local Model Watch
Last updated 2026-10-03 (JST). Facts above come from the GitHub API; the one-paragraph summary was written by the site’s operator with the help of AI.