io.github.MetriLLM/metrillm

not probeable (local package)

Unclaimed · Unverified

Publisher-provided description

Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client

Summary by lookupd

Lets an agent run benchmarks on local LLM models and get speed, quality, and hardware-fit verdicts for them.

Install

Claude Code, npm package (stdio)

claude mcp add metrillm -- npx -y metrillm-mcp

Codex, npm package (stdio)

codex mcp add metrillm -- npx -y metrillm-mcp

Cursor, npm package (stdio) → .cursor/mcp.json

{
  "mcpServers": {
    "metrillm": {
      "command": "npx",
      "args": [
        "-y",
        "metrillm-mcp"
      ]
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.MetriLLM/metrillm.svg)](https://lookupd.com/servers/io.github.MetriLLM/metrillm)