io.github.RudrenduPaul/inferbench

not probeable (local package)

Unclaimed · Unverified

Publisher-provided description

Benchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.

Summary by lookupd

Runs local LLM inference benchmarks on your own hardware and reports tokens-per-second throughput results.

Install

Claude Code, pypi package (stdio)

claude mcp add inferbench -- uvx inferbench-cli

Codex, pypi package (stdio)

codex mcp add inferbench -- uvx inferbench-cli

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

{
  "mcpServers": {
    "inferbench": {
      "command": "uvx",
      "args": [
        "inferbench-cli"
      ]
    }
  }
}

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.RudrenduPaul/inferbench.svg)](https://lookupd.com/servers/io.github.RudrenduPaul/inferbench)