All servers · AI models & agents · Code & repositories

Nodegrove VRAM: can I run it?

io.nodegrove/vram-mcp · v1.1.4

Measured by MCP Station

Description written by the publisher, not verified

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

Connect

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

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

Tools as reported by the server

• 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.

Repository · Website · JSON · Text for agents · Registry updated 2026-10-19