StudioTV LLM VRAM Calculator
Does an LLM fit on your GPU? VRAM, KV cache and GPU count for any Hugging Face model.
Connect it
Settings → Connectors → Add custom connector
URL: https://studiotvai.com/api/mcpSettings → Apps & Connectors → Advanced → Developer mode
Create connector with URL: https://studiotvai.com/api/mcp{
"mcpServers": {
"llm-vram": {
"url": "https://studiotvai.com/api/mcp"
}
}
}claude mcp add --transport http llm-vram https://studiotvai.com/api/mcp{
"servers": {
"llm-vram": {
"type": "http",
"url": "https://studiotvai.com/api/mcp"
}
}
}3 tools, verified live
estimate_vramread-onlyGPU 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).
models_that_fitread-onlyEvery listed open model that fits on the given GPU(s), largest first, with the most faithful weight format that fits.
gpu_pricesread-onlyCheapest 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.
Alternatives in AI & Agents
Compare →MAMakeOfficialA
Give your AI agents the tools to build, manage, and run automation workflows.
PAPaypalOfficialA
PayPal MCP server provides access to PayPal services and operations for AI assistants
SOSkill of SkillsA
Quality-ranked, cross-platform directory of AI coding skills, plugins and MCP servers.
KEKernelcadA
Agent-first CAD: editable .kcad.ts source, deterministic review, OpenCASCADE kernel.
EREu RegistryA
EU company registry lookup: 16 countries incl. Lithuania (JAR: identity + legal status).
DDDdA
Czech & EU due diligence in one call — facts, insolvency, sanctions, VAT, risk score, UBO chain.