MCP server

MarvinLabs vram_fit Official

org.marvinlabs/vram-fit

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

Will a QLoRA fine-tune of gemma-3-4b-it fit your GPU? Verdicts from measured AMD and NVIDIA probes.

Working at last checkVerified publisher: marvinlabs.orgAbout 709 tokens per request once connected3 tools

https://marvinlabs.org/mcp

At a glance

Type: MCP server
Publisher: marvinlabs.org (verified by the MCP Registry)
Status: Working at last check
Tools: 3
Token cost: About 709 tokens per request
Sets up in: Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok
Last checked: 26 Oct 2026, 08:29 UTC

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http vram-fit https://marvinlabs.org/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.vram-fit]
url = "https://marvinlabs.org/mcp"

Gemini CLI

{"mcpServers":{"vram-fit":{"httpUrl":"https://marvinlabs.org/mcp"}}}

Cursor

{"mcpServers":{"vram-fit":{"url":"https://marvinlabs.org/mcp"}}}

VS Code

{"servers":{"vram-fit":{"type":"http","url":"https://marvinlabs.org/mcp"}}}

Antigravity

agy mcp add vram-fit https://marvinlabs.org/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"vram-fit","server_url":"https://marvinlabs.org/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"vram-fit","server_url":"https://marvinlabs.org/mcp"}

vram_fit ~324 tokens
Will this LoRA config train on a card with vram_gb GB? Returns verdict fits / tight / does_not_fit, the predicted peak in MB, the margin, how each part was derived, and any measured probe with the same settings.
vram_max_rank ~269 tokens
Largest LoRA rank (multiple of 8) that fits with margin on a card with vram_gb GB, and the largest that is tight (a real run may fit, the one-step probe would not).
vram_probes ~116 tokens
The raw measured probe rows (RX 7900 XTX and RTX 3060 Ti), filtered by any of the given settings. gpu matches part of the card name, e.g. '7900' or '3060'.

compute.pangle.online — GPU rental market
Live GPU rental market: 2,500+ offers across a dozen provider feeds. History, watches, limit orders.
Together AI MCP by usefulapi
Run Together AI chat, embeddings and images; manage fine-tunes, batches and endpoints.
ACE-Step 1.5 jpdenpa full fine-tune
Full fine-tune of ACE-Step 1.5 turbo on Japanese songs
gpu.nz GPU cloud
Rent cloud GPUs from AI agents: live prices, VRAM estimates, launch, logs and stop.
Model Ruler — AI Cost Calculators
Read-only AI/LLM cost tools with current MCP discovery and attributable Registry transport.
HeatPulse
AI-news gateway for agents: curated events, digests, live LLM leaderboards, intent router.
Semancer 12B
Occult philosophy chat LLM fine-tuned on Gemma 4 12B
Mistral MCP by usefulapi
Manage your Mistral platform — models, files, batch jobs, agents and RAG document libraries.

[![AptLynx](https://aptlynx.net/badge/org.marvinlabs/vram-fit.svg)](https://aptlynx.net/servers/org.marvinlabs/vram-fit)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents