inferbench for Zed

io.github.rudrendupaul/inferbench

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

client:Zed transport:stdio runtime:pypi

Install inferbench in Zed

~/.config/zed/settings.json · windows: %APPDATA%\Zed\settings.json

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

Merge this into your existing settings object — do not replace the file. Zed docs