FitLLM MCP Server

FitLLM is an open-source, zero-dependency engine that checks whether a local LLM fits on a GPU or Apple Silicon Mac using architecture-aware memory math.

Remote server

What is the FitLLM MCP Server?

FitLLM is an MCP project maintained in the click6067-ship-it/fitllm-engine repository. The maintainer describes its purpose as “FitLLM is an open-source, zero-dependency engine that checks whether a local LLM fits on a GPU or Apple Silicon Mac using architecture-aware memory math”. Read the project documentation for the complete scope.

Hosted connection

The maintainer’s configuration uses https://fitllm.run/api/mcp. Check the project’s account and authentication instructions when adding the endpoint to your client.

Source

Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

ToolWhat it does
check_llm_fitcheck one model against a GPU, multi-GPU rig, or Mac and return the verdict, memory breakdown, and a fix when it does not fit.
what_fits_on_hardwarerank the supported local models that fit the given GPU, multi-GPU rig, or Mac.
list_supportedlist the built-in model and hardware names accepted by the fit checker.

How to install the FitLLM MCP Server

{
  "mcpServers": {
    "fitllm": {
      "url": "https://fitllm.run/api/mcp"
    }
  }
}

From the project documentation. Replace placeholders and example paths before connecting.