# FitLLM MCP server

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

## Links
- Registry page: https://www.getdrio.com/mcp/run-fitllm-fitllm
- Repository: https://github.com/click6067-ship-it/fitllm-engine
- Website: https://fitllm.run

## Install
- Endpoint: https://fitllm.run/api/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://fitllm.run/api/mcp

## Tools
- check_llm_fit (Check if an LLM fits on hardware) - 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 full memory breakdown (weights, KV cache, overhead), max context, and a concrete fix if it doesn't fit. Use this whenever a user asks anything like "can I run <model> on my <GPU/Mac>?", "will <model> fit in <N>GB?", or "what do I need to run <model>?". Architecture-aware math (MLA, sliding-window, hybrid attention, MoE) — more accurate than rule-of-thumb estimates. Endpoint: https://fitllm.run/api/mcp
- what_fits_on_hardware (What LLMs fit on this 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 naming a model. Endpoint: https://fitllm.run/api/mcp
- list_supported (List supported models & hardware) - List the built-in model names and hardware names this fit-checker knows (for mapping user wording to exact names). Any public HuggingFace model also works via fitllm.run. Endpoint: https://fitllm.run/api/mcp

## Resources
- fitllm://models - FitLLM model catalog Built-in local LLM catalog with the architecture fields the fit engine uses (layers, KV heads/dims, sliding window, MLA, hybrid attention, MoE). JSON. MIME type: application/json
- fitllm://hardware - FitLLM hardware catalog GPUs (VRAM, bandwidth, source-cited) and Apple Silicon chips (unified memory tiers) known to the engine. JSON. MIME type: application/json
- fitllm://census - FitLLM Fit Census (6,000+ verdicts) Every model × device × quant verdict computed by the engine — starter matrix inline; full CSV/JSON at fitllm.run/data. CC0 data. MIME type: text/markdown
- fitllm://engine - FitLLM engine — direct access The open MIT calculation engine behind every verdict: source, npm package, conformance vectors, versions. Agents may fetch and run it directly. MIME type: application/json

## Prompts
Not captured

## Metadata
- Owner: run.fitllm
- Version: 1.0.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 9, 2026
- Source: https://registry.modelcontextprotocol.io