Magnitude open-source inference server swaps coding agents to free local models automatically
nickbaumann_ · x · 2026-09-03
Magnitude (1.6k GitHub stars) is an open-source inference server that profiles your hardware, recommends the best local models, and plugs them into the coding agent you already use.
- Author demo: Hermes agent switched itself to 100% free local models via the Magnitude CLI, running Qwen 3.6 35B-A3B at 60 tok/s on a DGX Spark — free, private, always-on for background tasks
- The agent handles the migration itself: hardware profiling, model selection, and switchover; models load just-in-time and unload when idle
- Works with Pi, OpenCode, Hermes, OpenClaw, Codex, Claude Code, Oh My Pi, and Cline
- One-liner onboarding: npm i -g @magnitudedev/cli, then magnitude docs onboarding.
More from coding & agent
- XBOW explains how it deduplicates vulnerability findings when hunting bugs at scale — moyix · 2026-09-03
- fable-advisor: Fable 5.1 as architect orchestrating GPT implementers in Claude Code — daniel_mac8 · 2026-09-03
- Every launches Compound Writing: a Claude Code plugin that compounds your editorial feedback — danshipper · 2026-09-03
- video-shotcraft: open-source skill turns Claude Code into a cinematic product video studio with 157 shot recipes — tom_doerr · 2026-09-03
- Vercel Fluid Compute Now Runs 15M Builds Daily, Unifying Functions, Sandboxes and Builds on One System — soleio · 2026-09-03
- Exo agent harness draws buzz: full code exposed to models for recursive self-improvement — omarsar0 · 2026-09-03