# Nodegrove VRAM: can I run it?

- Registry name: `io.nodegrove/vram-mcp` · version 1.1.4
- Categories (automatic, keyword rules): AI models & agents, AI, media & content, Code & repositories, Developer tools
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.nodegrove%2Fvram-mcp
- Server page: https://mcpstation.net/s/io.nodegrove--vram-mcp.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://mcp.nodegrove.io/mcp`

## Tools (as reported by the server, not verified)

- `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 that fits and, on a no, every change that would make it fit: quantisation, KV cache, context, another card or a smaller model. Model: a name o
- `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 \(the biggest class that fits with room for context at conversational speed\), the largest that fits, the best at Q8 and the first out of reach. GPU: a name or id
- `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 each. Model: a name or id from list\_models, any Hugging Face repo id, or its architecture \(params\_b, layers, kv\_heads, head\_dim\).
- `estimate\_from\_hf\_repo`: Reads any Hugging Face model repo's config.json and parameter count and estimates its memory: the attention layout found \(standard, sliding-window, hybrid or latent\), how much each 1,000 tokens of context costs, and weights + KV cache + overhead at every quantisation. For models nodegrove.io has not
- `list\_models`: The open-weight LLMs nodegrove.io has verified against their config.json \(data version 2026-10-16\): id, size, attention design, native context, licence, memory at Q4 with 8k context and each model's page.
- `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.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html