Nodegrove VRAM: can I run it? MCP server

Can I run it?

An MCP server that tells your AI assistant whether an open-weight LLM fits your GPU, and what would fit instead. The arithmetic behind nodegrove.io, for any model on Hugging Face and any card.

Can my RTX 4090 run Llama 3.3 70B?

No: Llama 3.3 70B at Q4KM with 8,192 tokens of context needs 45.8 GB, and the RTX 4090 holds 22.8 GB after headroom. Short by 23 GB. What would work instead:

- No context length helps: the weights alone are 43.1 GB before a single token of conversation.

- RTX 6000 Ada (48 GB) is within a whisker: 45.8 GB against 45.6 GB after headroom. With the KV cache at Q8 it needs 44.4 GB and fits.

- The smallest card here that runs it exactly as asked: A100, 80 GB usable.

- The biggest model your card does run at these settings, counting mixture-of-experts models at their dense equivalent: Qwen3 32B, 22.4 GB at ~37 tokens/s.

That is the server's own answer, word for word. Every figure is a stated formula over the model's config.json and the card's published specs: no benchmarks, no guesses. It is free, read-only, and needs no account or key.

Connect

Remote: nothing to install

https://mcp.nodegrove.io/mcp

Claude (claude.ai and the desktop app)

Customize → Connectors → Add → Add custom connector. Name it Nodegrove VRAM, paste the URL, choose No sign-in, then turn it on in a chat from + → Connectors.

Claude Code

claude mcp add --transport http nodegrove-vram https://mcp.nodegrove.io/mcp

Add --scope user to have it in every project.

Cursor

~/.cursor/mcp.json:

{ "mcpServers": { "nodegrove-vram": { "url": "https://mcp.nodegrove.io/mcp" } } }

VS Code

.vscode/mcp.json:

{ "servers": { "nodegrove-vram": { "type": "http", "url": "https://mcp.nodegrove.io/mcp" } } }

Devin Desktop (formerly Windsurf)

devin mcp add -s user nodegrove-vram https://mcp.nodegrove.io/mcp

LM Studio

Program → Install → Edit mcp.json:

{ "mcpServers": { "nodegrove-vram": { "url": "https://mcp.nodegrove.io/mcp" } } }

Open WebUI

Admin Settings → Integrations → External Tool Servers → Add Connection. Type MCP (Streamable HTTP), the URL above, authentication None.

Shortened. The full README is on GitHub.