Nodegrove VRAM: can I run it? is an MCP server with 6 tools an agent can call, among them can_i_run, estimate_from_hf_repo, estimate_vram. It answers at https://mcp.nodegrove.io/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 3 October 2026; the last check, on 18 November 2026, succeeded.
Can this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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 cach Inputs: model, architecture, active_params_b, gpu, vram_gb, bandwidth_gb_s |
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 + ove Inputs: repo, active_params_b, context, kv_cache |
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 archit Inputs: model, architecture, active_params_b, quant, context, kv_cache |
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. Inputs: search |
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 at Q4 with 8k context and each model's page. Inputs: search |
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, t Inputs: gpu, vram_gb, bandwidth_gb_s, apple_silicon, quant, context |
Every block below points at https://mcp.nodegrove.io/mcp. Pick your client and copy.
claude mcp add --transport http nodegrove-vram-can-i-run-it https://mcp.nodegrove.io/mcp
{
"mcpServers": {
"nodegrove-vram-can-i-run-it": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.nodegrove.io/mcp"]
}
}
}{
"mcpServers": {
"nodegrove-vram-can-i-run-it": {
"url": "https://mcp.nodegrove.io/mcp"
}
}
}{
"servers": {
"nodegrove-vram-can-i-run-it": {
"type": "http",
"url": "https://mcp.nodegrove.io/mcp"
}
}
}{
"context_servers": {
"nodegrove-vram-can-i-run-it": {
"url": "https://mcp.nodegrove.io/mcp"
}
}
}{
"mcpServers": {
"nodegrove-vram-can-i-run-it": {
"serverUrl": "https://mcp.nodegrove.io/mcp"
}
}
}{
"mcpServers": {
"nodegrove-vram-can-i-run-it": {
"url": "https://mcp.nodegrove.io/mcp"
}
}
}name: Nodegrove VRAM: can I run it?
version: 0.0.1
schema: v1
mcpServers:
- name: Nodegrove VRAM: can I run it?
type: streamable-http
url: https://mcp.nodegrove.io/mcp{
"mcpServers": {
"nodegrove-vram-can-i-run-it": {
"httpUrl": "https://mcp.nodegrove.io/mcp"
}
}
}{
"mcpServers": {
"nodegrove-vram-can-i-run-it": {
"type": "http",
"url": "https://mcp.nodegrove.io/mcp"
}
}
}{
"mcpServers": {
"nodegrove-vram-can-i-run-it": {
"url": "https://mcp.nodegrove.io/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.nodegrove.io%2Fmcp&type=streamable_http&id=nodegrove-vram-can-i-run-it&name=Nodegrove%20VRAM%3A%20can%20I%20run%20it%3F
It answered our last check on 18 November 2026 in 340 ms. Over 4 checks since 3 October 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by nodegrove.io and served from mcp.nodegrove.io, the vendor's own domain: https://mcp.nodegrove.io/mcp.
6, as returned by the server's own tools/list on 20 November 2026: can_i_run, estimate_from_hf_repo, estimate_vram, list_gpus, list_models, what_fits.
It answered our last check on 18 November 2026 in 340 ms. Over 4 checks since 3 October 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.nodegrove.io/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.nodegrove. Endpoint host: mcp.nodegrove.io. ARD identifier: urn:air:io.nodegrove:mcp:vram-mcp.
First indexed 3 October 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.