Magnitude: free open-source desktop engine profiles your hardware, picks and tunes local models
nickbaumann_ · x · 2026-09-19
Magnitude is a 100% free, Apache 2.0 open-source desktop inference engine optimized for consumer hardware, natively on macOS, Windows and Linux — Apple Silicon, NVIDIA, AMD GPUs, or CPU-only.
Unlike Ollama or LM Studio which run whatever model you pick, Magnitude helps you pick: it profiles your hardware, estimates tok/s for every model before download, and ranks models by speed, accuracy, intelligence and memory. After you choose, it downloads and tunes the model end to end — context size, speculative decoding and more, configured for your exact machine.
It also one-click connects coding agents like Pi, OpenCode and Hermes, loads models on demand (unloading when idle or memory fills), and runs fully offline with no token costs, API keys or rate limits.
More from Infra
- lateinteraction: nobody writes RISC by hand — compilers abstract away chip bifurcation — lateinteraction · 2026-09-19
- AI Infra Summit: Penguin Solutions and Astera Labs Bet Big on CXL Memory Expansion — BenBajarin · 2026-09-19
- Jev seen as local-model stand-in for low-latency apps; open-weight RLCD models expected — HankYeomans · 2026-09-19
- Hands-On: Running On-Device VLM Inference on Arduino Ventuno Q's Hexagon NPU — HowDevelop · 2026-09-19
- GPU price hike hits even the 1080ti, as local LLM token-speed numbers circulate — HankYeomans · 2026-09-19
- Bonsai 2 27B quantized beats Gemma 4 12B and Qwen 3.5 9B in 7GB 3D generation test — Fun-Meaning-6474 · 2026-09-19