Benchmark local LLM models: speed, quality, and hardware fitness scoring. CLI, MCP server, and IDE plugins.
Latest release v0.2.6 · 16 Mar 2026
2 files for Codex, OpenCode and Claude Code: metrillm AGENTS.md, metrillm CLAUDE.md — 2,834 tokens loaded in every session.
AGENTS.md A 1,187 tok CLAUDE.md A 1,647 tok These files are MetriLLM/metrillm's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.