FitLLM

Last 30 days

Uptime

100%

Response time

303 ms typical, 303 ms slowest 5%

Last check

5 h ago

Next check

in 55 min

How to call it

Add it to any MCP client that supports remote servers.

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

3 tools

• check_llm_fit

  Check whether a specific local LLM fits in the memory of a specific GPU or Apple Silicon Mac. Returns fits/tight/won't-fit verdict with the memory breakdown (weights, KV cache, linear-attention state when present, runtime overhead, reserve), max context, and a concrete fix if it

• what_fits_on_hardware

  Rank which popular local LLMs fit on a given GPU or Apple Silicon Mac (at ~4-bit quantization, 8K context) — models that fit come first, biggest first, with max context each. Use when a user asks "what can I run on my <GPU/Mac/N GB>?", "best local model for my machine?", or gives

• list_supported

  List the built-in model names and hardware names this fit-checker knows (for mapping user wording to exact names). Standard text-only HuggingFace transformer configs can also be checked via fitllm.run; unsupported architectures are rejected.

Security scan

• No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks