{"name":"magnitude","repo":"magnitudedev/magnitude","url":"https://midorreal.com/project/magnitudedev-magnitude","repository":"https://github.com/magnitudedev/magnitude","description":"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, Intel, or just a CPU.","facts":{"license":{"value":"Apache-2.0","source":"https://github.com/magnitudedev/magnitude","checked":"22 Nov 2026"},"language":{"value":"Rust","source":"https://github.com/magnitudedev/magnitude","checked":"22 Nov 2026"},"homepage":{"value":"https://magnitude.dev","source":"https://magnitude.dev","checked":"22 Nov 2026"},"last_release":{"value":"@magnitudedev/cli@0.2.98, 20 Nov 2026","source":"https://github.com/magnitudedev/magnitude/releases","checked":"22 Nov 2026"},"releases":{"value":"89","source":"https://github.com/magnitudedev/magnitude/releases","checked":"20 Nov 2026"},"contributors":{"value":"13","source":"https://github.com/magnitudedev/magnitude/graphs/contributors","checked":"20 Nov 2026"},"archived":{"value":"no","source":"https://github.com/magnitudedev/magnitude","checked":"22 Nov 2026"}},"stars":8128.0,"writeup":{"what_it_is":"Magnitude is an open source inference engine that tunes its kernels for each model on the user's hardware. It ships as a desktop app and CLI, and connects to agents such as Pi, OpenCode, Hermes and Codex.","audience":"Developers and users who run open-weight models locally on their own hardware","claims":[{"kind":"specific","claim":"Over 2x faster than Ollama on average across popular local models","excerpt":"It's over 2x faster than Ollama and works on Apple Silicon, NVIDIA, AMD, Intel, or just a CPU","status":"not_checked"},{"kind":"specific","claim":"Kernels are tuned for each model when it is downloaded","excerpt":"kernels are tuned for each model when you download it","status":"not_checked"},{"kind":"specific","claim":"Works on Apple Silicon, NVIDIA, AMD, Intel GPUs, or CPU only","excerpt":"Any Apple Silicon, NVIDIA, AMD, or Intel GPU, or nothing but a CPU","status":"not_checked"},{"kind":"specific","claim":"Each model ships with a speculative decoding drafter","excerpt":"each model ships with the fastest speculative decoding drafter","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-10-27"},"why_now":null,"owner_supplied":null,"score":{"verdict":"real","hype":78,"reality":96,"gap":-18,"momentum":1.8,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-11-20T09:38:51+00:00","text":"Latest release @magnitudedev/cli@0.2.98","source":"https://github.com/magnitudedev/magnitude/releases"},{"date":"2026-06-12T09:14:39+00:00","text":"First release","source":"https://github.com/magnitudedev/magnitude/releases"},{"date":"2026-06-12T09:06:26+00:00","text":"Repository created","source":"https://github.com/magnitudedev/magnitude"}],"cite":"magnitude is a GitHub project at https://github.com/magnitudedev/magnitude written mainly in Rust, described there as \"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, Intel, or just a CPU\".","attribution":"Data from Mid or Real, https://midorreal.com/project/magnitudedev-magnitude, checked 22 November 2026. Attribution with a link is required.","still_real":null}