Ermittelt, ob Open-Weight LLMs auf spezifische GPUs passen, und liefert Hardware-Empfehlungen sowie VRAM-Schätzungen.
Auch bekannt als nodegrove/vram-mcp, vram-mcp, @nodegrove/vram-mcp
- Stars
- 0
- Tools
- 4
- Downloads, 30 Tage
- —
- Neueste Version
- 1.1.5
- Letzter Commit
- 3. Nov. 2026
- Lizenz
- MIT
Was ist Nodegrove VRAM MCP?
Ermittelt, ob Open-Weight LLMs auf spezifische GPUs passen, und liefert Hardware-Empfehlungen sowie VRAM-Schätzungen. Er stellt 4 Tools bereit, etwa can_i_run, what_fits, estimate_vram.
Zusammenfassung generiert aus dem README des Projekts
Über Nodegrove VRAM MCP server
Nodegrove VRAM ist ein MCP server für Entwickler und KI-Enthusiasten, die prüfen müssen, ob bestimmte Open-Weight Large Language Models auf ihrer Hardware laufen können. Er liefert präzise VRAM-Schätzungen, indem er die kombinierten Anforderungen aus Modellgewichten, KV Cache und Overhead berechnet. Der Server nutzt echte Modell-Konfigurationsdateien und Hardware-Spezifikationen anstelle von Benchmarks oder Schätzungen, um Genauigkeit zu gewährleisten.
Nutzer können sich remote über eine gehostete URL mit diesem Server verbinden oder ihn lokal mit Node.js und stdio ausführen. Er funktioniert mit verschiedenen KI-Clients wie Claude, Cursor, VS Code und LM Studio. Für die Nutzung des Services sind keine Accounts oder API-Keys erforderlich. Der Server bietet spezialisierte Tools wie can_i_run, um die Kompatibilität für spezifische Context Lengths zu prüfen, und what_fits, um die besten Modelle für eine bestimmte GPU zu finden. Er enthält außerdem estimate_vram und estimate_from_hf_repo, um jedes Hugging Face Repository durch direktes Lesen der config.json Datei zu analysieren.
Was du damit machen kannst
- 1Modell-Hardware-Kompatibilität prüfenErmittle, ob ein spezifisches Modell wie Llama 3.3 70B bei einer festgelegten Context Length auf eine RTX 4090 passt.
- 2Optimale Modelle für Hardware findenIdentifiziere die größten oder leistungsstärksten Modelle, die auf einer bestimmten Grafikkarte laufen können.
- 3VRAM für spezifische Einstellungen schätzenErhalte eine Aufschlüsselung der Anforderungen für Gewichte und KV Cache eines Modells bei einem bestimmten Quantisierungslevel.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
So installierst du Nodegrove VRAM MCP
Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügenZu Goose hinzufügenNodegrove VRAM MCP in Claude Code installieren
$ claude mcp add vram-mcp -- npx -y @nodegrove/vram-mcpNodegrove VRAM MCP in Cursor installieren
~/.cursor/mcp.json
{
"mcpServers": {
"vram-mcp": {
"command": "npx",
"args": [
"-y",
"@nodegrove/vram-mcp"
]
}
}
}Nodegrove VRAM MCP in VS Code installieren
.vscode/mcp.json
{
"servers": {
"vram-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@nodegrove/vram-mcp"
]
}
}
}Nodegrove VRAM MCP in VS Code CLI installieren
$ code --add-mcp '{"name":"vram-mcp","type":"stdio","command":"npx","args":["-y","@nodegrove/vram-mcp"]}'Nodegrove VRAM MCP in Claude Desktop installieren
claude_desktop_config.json
{
"mcpServers": {
"vram-mcp": {
"command": "npx",
"args": [
"-y",
"@nodegrove/vram-mcp"
]
}
}
}Nodegrove VRAM MCP in Codex installieren
$ codex mcp add vram-mcp -- npx -y @nodegrove/vram-mcpNodegrove VRAM MCP in Codex config.toml installieren
~/.codex/config.toml
[mcp_servers.vram-mcp] command = "npx" args = ["-y", "@nodegrove/vram-mcp"]
Nodegrove VRAM MCP in Gemini CLI installieren
$ gemini mcp add -s user vram-mcp npx -- -y @nodegrove/vram-mcpNodegrove VRAM MCP in Gemini settings.json installieren
~/.gemini/settings.json
{
"mcpServers": {
"vram-mcp": {
"command": "npx",
"args": [
"-y",
"@nodegrove/vram-mcp"
]
}
}
}Nodegrove VRAM MCP tools 4
Erkannt aus dem READMEcan_i_runwhat_fitsestimate_vramestimate_from_hf_repo
| can_i_run | — | |
| what_fits | — | |
| estimate_vram | — | |
| estimate_from_hf_repo | — |
Automatisierte Checks
Geluften am 13. Nov. 2026Vollständiger Bericht →Unsere automatisierten Checks bestanden. Das ist kein Security-Audit: Lies den Code und gib dem Server nur den minimal notwendigen Zugriff. Wie die Checks funktionieren
- Source Repository verknüpft und erreichbarnodegrove/vram-mcp is public and reachablegithub.com/nodegrove/vram-mcp ↗Bestanden
- Paket nennt dieses Repository als Quelle@nodegrove/vram-mcp names nodegrove/vram-mcp as sourcenpmjs.com/package/@nodegrove/vram-mcp ↗Bestanden
- Build-Provenienz (Sigstore-Attestierung)No build attestation published for this releaseNicht geprüft
- Open Source Lizenz (OSI)MITspdx.org/licenses/MIT.html ↗Bestanden
- Commit oder Release im letzten JahrLast commit or release 2026-11-03github.com/nodegrove/vram-mcp ↗Bestanden
- OpenSSF ScorecardNicht geprüft
- Package-Name ähnelt keinem populären PackageNo popular package one edit away from @nodegrove/vram-mcpBestanden
- Keine kritischen Advisories im Paket oder seinen Abhängigkeiten4 resolved dependencies checked; no critical advisoryosv.dev ↗Bestanden
- Keine versteckten Anweisungen an das Modell4 tool descriptions and the README read; no override phrases, credential paths or hidden charactersBestanden
- Destruktive Tools sind markiertNo tool named like delete, drop or execBestanden
- Remote-Endpoint beantwortet den MCP-Handshakeinitialize answered with protocol 2025-06-18 in 205 msBestanden
README
Auf GitHub ansehenCan my RTX 4090 run Llama 3.3 70B?
No: Llama 3.3 70B at Q4_K_M with 8,192 tokens of context needs 45.8 GB, and the RTX 4090 holds 22.8 GB after headroom. Short by 23 GB. What would work instead:
- No context length helps: the weights alone are 43.1 GB before a single token of conversation.
- RTX 6000 Ada (48 GB) is within a whisker: 45.8 GB against 45.6 GB after headroom. With the KV cache at Q8 it needs 44.4 GB and fits.
- The smallest card here that runs it exactly as asked: A100, 80 GB usable.
- The biggest model your card does run at these settings, counting mixture-of-experts models at their dense equivalent: Gemma 4 31B, 20.9 GB at ~39 tokens/s.
That is the server's own answer, word for word, from the same code as the GPU compatibility checker on nodegrove.io. Every figure is a stated formula over the model's config.json and the card's published specs: no benchmarks, no guesses. It is free, read-only, and needs no account or key.
Connect
Remote: nothing to install
https://mcp.nodegrove.io/mcp
# Claude Code (add --scope user to have it in every project)
claude mcp add --transport http nodegrove-vram https://mcp.nodegrove.io/mcp
# Codex CLI
codex mcp add nodegrove-vram --url https://mcp.nodegrove.io/mcp
# Gemini CLI
gemini mcp add -s user --transport http nodegrove-vram https://mcp.nodegrove.io/mcp
- Claude (claude.ai and the desktop app): Customize → Connectors → Add → Add custom connector. Name it
Nodegrove VRAM, paste the URL, choose No sign-in, then turn it on in a chat from + → Connectors. - ChatGPT: Settings → Security and login → turn on Developer mode. At chatgpt.com/plugins, add the URL with No Authentication, then pick it in a chat from + → Developer mode.
Most other clients take this in their mcp.json. Cline, Zed, Open WebUI, Devin Desktop and the rest are covered step by step at nodegrove.io/mcp.
{ "mcpServers": { "nodegrove-vram": { "url": "https://mcp.nodegrove.io/mcp" } } }
Local: over stdio
Needs Node.js 20 or newer:
{
"mcpServers": {
"nodegrove-vram": {
"command": "npx",
"args": ["-y", "@nodegrove/vram-mcp"]
}
}
}
Tools
| Tool | Ask it | It answers with |
|---|---|---|
can_i_run |
Can my RTX 4090 run Llama 3.3 70B with 32k of context? | Fits, tight or no; the memory split; a speed ceiling; the longest context that fits; and on a no, every change that would make it fit |
what_fits |
What is the best model for my 16 GB card? | Every model checked on one card, with a recommended everyday pick, the largest that fits, the best at Q8 and the first out of reach |
estimate_vram |
How much VRAM does Qwen3 32B need at 64k? | Weights, KV cache and overhead at each quantisation, and the smallest common card that holds each |
estimate_from_hf_repo |
How much memory does Qwen/Qwen3-Next-80B-A3B-Instruct need? |
Any Hugging Face repo, read from its config.json: the attention layout, the cost of each 1,000 tokens of context, and memory at every quantisation |
list_models, list_gpus |
Which GPUs do you know? | The models and cards with their specs, ids and pages |
Models can be named the way people type them ("llama 3.3 70b", Llama-3.3-70B-Instruct) or given as any Hugging Face repo id. Cards can be named ("4090", "M4 Max") or described by their memory and bandwidth. Every answer carries the numbers as fields, links to the model and card pages on nodegrove.io, and the assumptions behind each figure. All six tools are read-only.
How the numbers are made
- Memory is weights + KV cache + overhead. Weights are parameters × bytes per parameter at the quantisation: FP16 2.00, Q8_0 1.06, Q6_K 0.82, Q5_K_M 0.71, Q4_K_M 0.58, Q3_K_M 0.47. Overhead is 0.5 GB plus 4% of the weights.
- The KV cache is counted the way each model caches. Sliding-window layers stop at their window, hybrid models (linear attention or Mamba) grow a cache only on their few full-attention layers, and latent attention stores one compressed vector per layer. A standard-transformer formula would overstate these models several times over at long context.
- Fit means at most 95% of the memory a runtime can address; above 85% it is tight. Apple silicon gives the GPU about 75% of unified memory.
- Speed is 0.7 × memory bandwidth ÷ bytes of active weights read per token. It is a single-stream ceiling, not a measurement, and the faster the figure, the further real runtimes fall below it.
- The model table was read from each model's
config.jsonand checked against Hugging Face. Any other repo is read live by the same rules, which reproduce every row of the table; anything the reader cannot model is named in the answer, never guessed.
The full method, with every constant, is at nodegrove.io/data. The same figures are an open dataset under CC BY 4.0, DOI 10.5281/zenodo.22966137.
The math as a library
The server is a thin layer over @nodegrove/llm-math, the package nodegrove.io's pages and calculators are built on:
npm install @nodegrove/llm-math
import { modelById, estimate } from '@nodegrove/llm-math';
estimate({ ...modelById('llama-3.3-70b')!, quant: 'q4', context: 8192 }).totalGb; // 45.77
Privacy
The remote server runs on Cloudflare Workers. Nodegrove keeps no request logs and no record of what you ask: each request is answered by a fresh, stateless instance and forgotten. Cloudflare keeps standard edge logs for a short period, as for any website. Requests are rate-limited to 120 a minute per address. When you ask about a Hugging Face repo, the server fetches that repo's public config.json and metadata; only the repo name is sent. The local version contacts nothing but huggingface.co, and only when you ask about a repo there. Details: nodegrove.io/privacy.
Run your own
The remote endpoint is mcp/src/worker.ts. To deploy a copy to your Cloudflare account, change the route in mcp/wrangler.jsonc, then:
cd mcp && npm install && npx wrangler deploy
Development
cd llm-math && npm install && npm test
cd mcp && npm install && npm test && npm run build
llm-math/ is the package of formulas and data; mcp/ is the server, with the stdio entry (src/stdio.ts), the Worker (src/worker.ts) and the tools (src/tools.ts). This repository is published from Nodegrove's main repository, where the site uses the same package. Issues and pull requests are welcome here; accepted changes are applied upstream and credited.
Found a figure that disagrees with its source? Open an issue with the model or card and the link. To report a security problem, see SECURITY.md.
Licence
The code is MIT. The model and GPU data, llm-math/src/models.ts and llm-math/src/gpus.ts, is CC BY 4.0: use it for anything, and credit Nodegrove (nodegrove.io).
Model and GPU names are trademarks of their owners.
Nodegrove VRAM MCP Fragen
Wie füge ich Nodegrove VRAM MCP zu Claude Code hinzu?
Führe claude mcp add vram-mcp -- npx -y @nodegrove/vram-mcp in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.
Wie füge ich Nodegrove VRAM MCP zu Cursor hinzu?
Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.
Welche Tools bietet Nodegrove VRAM MCP?
Er stellt 4 Tools bereit, darunter can_i_run, what_fits, estimate_vram, estimate_from_hf_repo.
Wie berechnet der Server den VRAM-Bedarf?
Er berechnet den Speicher als Summe aus Gewichten, KV Cache und Overhead unter Verwendung spezifischer Formeln für verschiedene Modellarchitekturen wie Sliding-Window- oder Hybrid-Modelle.
Ist der Server kostenlos nutzbar?
Ja, der Server ist kostenlos, read-only und erfordert weder ein Konto noch einen API-Key.