FitLLM — Claude Code MCP server: what it does, how to install
Checks whether a local LLM fits in the memory of your GPU, multi-GPU rig or Mac, with the VRAM and KV-cache math behind the verdict.
claude mcp add --transport http fitllm https://fitllm.run/api/mcpWhat FitLLM does
FitLLM answers one question: will this model fit? You give it a model and your hardware, it works out weight and KV-cache memory from the model's architecture, and it returns a verdict. The hardware can be a single GPU, several GPUs together, or an Apple Silicon Mac.
It connects as a remote MCP server over Streamable HTTP, so nothing is installed locally. Three tools sit behind it: check_llm_fit handles one model and suggests a change when it falls short, what_fits_on_hardware ranks the models your machine can run, and list_supported shows the model and hardware names the checker knows.
The server is read-only, keeps no state and asks for no login. The flip side is that model and hardware names go to fitllm.run. If the agent can't match a name, call list_supported first.
What it helps with
- check whether a model fits before you download it
- see which local models your Mac can run
- find out what to change when a model doesn't fit
- estimate memory on a rig with several GPUs
- look up the model and GPU names the checker accepts
Example prompts for the agent
- Ask fitllm whether Gemma 4 12b fits on an RTX 4090
- Use fitllm to pick models that will run on my Mac
- Call
list_supportedfrom fitllm and show me the GPU names it knows
How to install FitLLM
Platform CLI: remote server
claude mcp add --transport http fitllm https://fitllm.run/api/mcpPlatform CLI: remote server
codex mcp add fitllm --url https://fitllm.run/api/mcpConfig file
{
"mcpServers": {
"fitllm": {
"url": "https://fitllm.run/api/mcp"
}
}
}Config file
{
"servers": {
"fitllm": {
"type": "http",
"url": "https://fitllm.run/api/mcp"
}
}
}Platform CLI: remote server
gemini mcp add -t http fitllm https://fitllm.run/api/mcpStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about FitLLM
How do I install FitLLM in Claude Code?
Run claude mcp add --transport http fitllm https://fitllm.run/api/mcp. The server is remote, so there is nothing else to install.
What does FitLLM do?
It estimates weight and KV-cache memory from a model's architecture and tells you whether the model fits your hardware. When it doesn't, check_llm_fit suggests what to change.
Does FitLLM need an API key or login?
No. The server needs no authentication, only reads data and keeps no state.
