Nodegrove VRAM: can I run it? — Claude Code MCP server
Works out whether an open-weight model fits in your card's memory, how much context survives, and what to run instead. Handy before you start a local model.
claude mcp add --transport http vram-mcp https://mcp.nodegrove.io/mcpWhat Nodegrove VRAM: can I run it? does
Ask it something like whether an RTX 4090 handles Llama 3.3 70B at 32k, and it answers in fields: fits, tight or no, the split between weights, KV cache and overhead, a speed ceiling, and the longest context that still works. On a no it lists the changes that would make the model fit. Models go in as people type them or as any Hugging Face repo id; cards by name or by their memory and bandwidth.
Six tools sit behind it: can_i_run, what_fits, estimate_vram, estimate_from_hf_repo, list_models and list_gpus. A foreign repo is read from its config.json. Anything the maths cannot cover gets named in the answer rather than guessed at, and every tool only reads. Memory is counted per architecture: sliding-window layers cap their cache at the window, hybrid models grow one on the few full-attention layers, so a plain transformer formula would overshoot badly at long context.
The remote server lives at https://mcp.nodegrove.io/mcp and asks for no account or key. For a local one use npx -y @nodegrove/vram-mcp, which needs Node.js 20 or newer. The speed figure is a single-stream ceiling, not a benchmark; real runtimes come in lower, and the higher the number the wider the gap.
What it helps with
- Check whether a model fits your card before downloading the weights
- Pick a context length that stays inside VRAM
- Find a replacement for a model that does not fit
- Compare memory cost across quantisations
- Estimate a card that is not in the ready-made tables
Example prompts for the agent
- Will Qwen3 32B fit on 24 GB at 64k context?
- What should I run instead of Llama 3.3 70B on a 16 GB card?
- How much memory does
Qwen/Qwen3-Next-80B-A3B-Instructtake at Q4_K_M?
How to install Nodegrove VRAM: can I run it?
1Platform CLI: remote server
claude mcp add --transport http vram-mcp https://mcp.nodegrove.io/mcp2Platform CLI
claude mcp add nodegrove-vram-can-i-run-it -- npx -y @nodegrove/vram-mcp1Platform CLI: remote server
codex mcp add nodegrove-vram-can-i-run-it --url https://mcp.nodegrove.io/mcp2Platform CLI
codex mcp add nodegrove-vram-can-i-run-it -- npx -y @nodegrove/vram-mcpConfig file
{
"mcpServers": {
"nodegrove-vram-can-i-run-it": {
"url": "https://mcp.nodegrove.io/mcp"
}
}
}{
"mcpServers": {
"nodegrove-vram-can-i-run-it": {
"command": "npx",
"args": [
"-y",
"@nodegrove/vram-mcp"
]
}
}
}Config file
{
"servers": {
"nodegrove-vram-can-i-run-it": {
"type": "http",
"url": "https://mcp.nodegrove.io/mcp"
}
}
}{
"servers": {
"nodegrove-vram-can-i-run-it": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@nodegrove/vram-mcp"
]
}
}
}1Platform CLI: remote server
gemini mcp add -t http nodegrove-vram-can-i-run-it https://mcp.nodegrove.io/mcp2Platform CLI
gemini mcp add nodegrove-vram-can-i-run-it npx -y @nodegrove/vram-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 Nodegrove VRAM: can I run it?
How do I install Nodegrove VRAM: can I run it? in Claude Code?
Run claude mcp add --transport http nodegrove-vram-can-i-run-it https://mcp.nodegrove.io/mcp for the remote server. For the local one, run claude mcp add nodegrove-vram-can-i-run-it -- npx -y @nodegrove/vram-mcp.
What does this server do?
It works out from stated formulas whether an open model fits your GPU memory, how much context it can hold and what speed ceiling applies. When it does not fit, it shows what to change.
Do I need an API key?
No. The remote endpoint runs without sign-in, and the local package needs Node.js 20 or newer.
