StudioTV LLM VRAM Calculator

com.studiotvaiPublished by studiotvai.comOfficial publisherv1.0.0Updated Oct 26, 2026

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

VerifiedStreamable HTTPWeb executableCloud & InfrastructureAI & ML

Overview

AI-generated overview

Estimates GPU VRAM, GPU count, speed and rental cost for running open LLMs, and lists models that fit given GPUs.

What you can do
  • Estimate VRAM, GPU count, speed and rental cost for a model on chosen GPUs
  • Check any listed open model or Hugging Face model id or link
  • List every listed model that fits the given GPUs, largest first, with the most faithful weight format
  • Compare cheapest on-demand GPU-hour prices across major cloud and GPU rental providers
When to use it
Useful when planning to self-host or rent GPUs for an open LLM and you want a quick fit, memory and cost estimate before committing to hardware or a provider.
Requirements
Remote MCP endpoint at studiotvai.com over streamable HTTP; no authentication, environment variables or headers declared. Network access to the endpoint is needed.
Before you install
Estimates and prices are advisory and may not match real throughput or billing; verify before renting GPUs. Model coverage depends on the provider's listed models plus Hugging Face ids.

Installation

In SourceWeft

  1. Open StudioTV LLM VRAM Calculator in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.studiotvai%2Fllm-vram/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "studiotv-llm-vram-calculator": {
      "type": "http",
      "url": "https://studiotvai.com/api/mcp"
    }
  }
}

Tools

3

estimate_vram

Does this LLM fit on this GPU?

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).

Parametersgpumodelrequiredenginecontextweightskv_cachegpu_countconcurrent_requests

models_that_fit

Which LLMs fit on this GPU?

Every listed open model that fits on the given GPU(s), largest first, with the most faithful weight format that fits.

Parametersgpurequiredenginecontextweightskv_cachegpu_countconcurrent_requests

gpu_prices

GPU rental prices

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.

Parametersgpu

Version history

1
  1. v1.0.0LatestOct 10, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.