MCP server · Developer tools

quelllm MCP server

Lets your AI look up open-source AI models, compare them, and estimate memory and cost for you.

Developer tools For it and development Developer Tools

This is a small helper that connects your AI assistant to a catalog of over 190 open-source AI models listed on quelllm.fr. It is handy if you are trying to pick a model to run on your own computer or compare what different AI services cost. You ask in plain words, and your AI looks things up for you.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to an outside service. This one connects your AI to the quelllm.fr catalog of open-source AI models. Once it is connected, your AI can look up models, compare them, and do quick math for you when you ask.

What this MCP server does

You ask your AI a question, like which models fit on a certain graphics card. Your AI sends that question to this helper. The helper looks it up in the quelllm.fr catalog and does the calculations. Then your AI tells you the answer in the chat, in normal words.

Flow diagram: you ask your AI “Which Mistral models run on a 16GB RTX 5070 Ti?”, the quelllm MCP server connects it to quelllm.fr catalog, and you get back plain answer in your chat.

Click to zoom

What you can do with it

List open-source AI models that match a family, source, or size
Look up full details for one model, like size, license, and links
Compare two models side by side with a short verdict
Estimate how much memory a model needs at a chosen compression level
Estimate monthly cost for API providers versus running it yourself
Search the catalog by name, author, or tag

Try asking your AI

“Which Mistral models can run on an RTX 5070 Ti with 16GB of memory?”
“Compare Llama 3.3 70B and Qwen 2.5 32B”
“I use 10 million input tokens and 2.5 million output tokens per month. How much would OpenAI cost versus DeepSeek?”
“Show me small models under 10 billion parameters”

What it gives back to you

You get back plain answers in the chat: lists of models, a side-by-side comparison, a memory estimate in gigabytes, or a cost table in euros. It also suggests which graphics cards or Macs could run a model. Nothing is changed anywhere; it only reads and calculates.

Before you start

What you need

Python installed on your computer (for the pip install option)
Or the uv tool installed (for the zero-install uvx option)
An MCP-compatible app like Claude Code, Claude Desktop, Cursor, Continue, or Cline

Good to know

The pricing and hardware numbers are hardcoded as of May 2026, so treat cost and hardware estimates as rough and check them again later.

Install it with your AI

Add quelllm MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check quelllm MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.