AIHacker Newsabout 1 hour ago
Magnitude Launches Self-Optimizing Inference Engine
2 min read
Magnitude, a Y Combinator S25 startup, launched an open source inference engine that compiles and tunes kernels on your device, claiming up to 2x faster performance than llama.cpp. It ships as a desktop app for macOS, Windows and Linux, connects to agents like Pi, OpenCode, Hermes and Codex, and runs on Apple Silicon, NVIDIA, AMD or CPU.
Level
Hype check
Tap to vote and see what everyone thinks.
