io.nodegrove/vram-mcp

up checked 2026-11-11T11:39:10.034Z

Unclaimed · Unverified

Publisher-provided title

Nodegrove VRAM: can I run it?

Publisher-provided description

Can this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU.

Summary by lookupd

Estimates whether open-weight LLMs fit a given GPU, reporting memory split, decode-speed ceiling, and models that fit.

Install

Claude Code, remote (streamable-http)

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

Claude Code, npm package (stdio)

claude mcp add vram -- npx -y @nodegrove/vram-mcp

Codex, remote (streamable-http)

codex mcp add vram --url https://mcp.nodegrove.io/mcp

Codex, npm package (stdio)

codex mcp add vram -- npx -y @nodegrove/vram-mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

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

Cursor, npm package (stdio) → .cursor/mcp.json

{
  "mcpServers": {
    "vram": {
      "command": "npx",
      "args": [
        "-y",
        "@nodegrove/vram-mcp"
      ]
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

can_i_run Can this GPU run this open-weight LLM? Returns fits, tight or no, the memory split (weights, KV cache, overhead), a decode-speed ceiling, the longest context th
what_fits Which open-weight LLMs fit this GPU: every model in list_models checked at one quantisation and context, with a recommended everyday model (the biggest class th
estimate_vram How much memory an LLM needs: weights + KV cache + overhead at each quantisation (or one), at a given context, and the smallest common card class that holds eac
estimate_from_hf_repo Reads any Hugging Face model repo's config.json and parameter count and estimates its memory: the attention layout found (standard, sliding-window, hybrid or la
list_models The open-weight LLMs nodegrove.io has verified against their config.json (data version 2026-11-03): id, size, attention design, native context, licence, memory
list_gpus The GPUs and machines nodegrove.io covers: memory, the memory a runtime can use and bandwidth, from the makers' specs, with each one's page.

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.nodegrove/vram-mcp.svg)](https://lookupd.com/servers/io.nodegrove/vram-mcp)