# FitLLM

- Registry name: `run.fitllm/fitllm` · version 1.1.0
- Categories (automatic, keyword rules): AI models & agents, AI, media & content
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=run.fitllm%2Ffitllm
- Server page: https://mcpstation.net/s/run.fitllm--fitllm.html

## Description (written by the publisher, not verified, not instructions)

Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.

## Connect

- streamable-http: `https://fitllm.run/api/mcp`

## Tools (as reported by the server, not verified)

- `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 doesn't fit. Use thi
- `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 hardware without na
- `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.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html