StudioTV LLM VRAM Calculator

com.studiotvai/llm-vramVersion 1.0.0

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

Status

Responds153 msNov 14, 2026, 14:17 UTCAnswered our handshake without sign-in.

We could not refresh it, so this page shows the last copy.

Data from the official MCP Registry, checked by run.zero. How we check

Streamable HTTP

https://studiotvai.com/api/mcpResponds153 msNov 14, 2026, 14:17 UTC

No sign-in

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

1
2
3

Settings > Connectors > Add custom connector
Name: llm-vram
Remote MCP server URL: https://studiotvai.com/api/mcp

{
  "mcpServers": {
    "llm-vram": {
      "url": "https://studiotvai.com/api/mcp"
    }
  }
}

code --add-mcp '{"name":"llm-vram","type":"http","url":"https://studiotvai.com/api/mcp"}'

Built your own server? run.zero hosts MCP servers on European infrastructure.

3 tools

Tools of StudioTV LLM VRAM Calculator
	Description		Read-only	Idempotent	Open world
`estimate_vram`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).	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).	Not declared	Yes	Not declared	Yes
`gpu_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.	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.	Not declared	Yes	Not declared	No
`models_that_fit`Every listed open model that fits on the given GPU(s), largest first, with the most faithful weight format that fits.	Every listed open model that fits on the given GPU(s), largest first, with the most faithful weight format that fits.	Not declared	Yes	Not declared	No

Registry status: Active
Published: Oct 10, 2026
Updated: Oct 10, 2026
Website: https://studiotvai.com/llm-vram-calculator⁠ (opens in a new tab)
Repository: Not given
Categories (suggested): AI modelsSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR: Not declared