Skip to content

StudioTV LLM VRAM Calculator

by studiotvai.com · remote · no sign-in to list tools · v1.0.0 · published by com.studiotvai

Does an LLM fit on your GPU? VRAM, KV cache and GPU count for any Hugging Face model.

Changes · 3
CompareRegistry entry

3 tools: 3 change things.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http llm-vram https://studiotvai.com/api/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

3 tools

Changes things 3Claude Code: ask
  • estimate_vramGPU memory, number of GPUs, speed and rental cost to run an open LLM.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    GPU memory, number of GPUs, speed and rental cost to run an open LLM. Works for the models listed at https://studiotvai.com/api/models.json and any Hugging Face model id or link. Uses the real KV cache of each architecture (sliding window, hybrid linear attention, MLA).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • gpu_pricesCheapest on-demand price per GPU-hour from AWS, Google Cloud, Azure, RunPod, Vast.ai, Oracle Cloud, OVHcloud, Scaleway, Verda, Akash and UpCloud, checked every hour.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Cheapest on-demand price per GPU-hour from AWS, Google Cloud, Azure, RunPod, Vast.ai, Oracle Cloud, OVHcloud, Scaleway, Verda, Akash and UpCloud, checked every hour.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • models_that_fitEvery listed open model that fits on the given GPU(s), largest first, with the most faithful weight format that fits.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Every listed open model that fits on the given GPU(s), largest first, with the most faithful weight format that fits.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http llm-vram https://studiotvai.com/api/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__llm-vram__estimate_vram",
      "mcp__llm-vram__models_that_fit",
      "mcp__llm-vram__gpu_prices"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as llm-vram. Review it before you use it.