com.studiotvai/llm-vram

StudioTV LLM VRAM Calculator

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

1.0.0
Version
remote
Transport
3
Tools

Security review

Review passed

Reviewed 21h ago.

  • tools: 3 tools scanned
  • metadata: scanned

No findings.

Tools (3)

  • 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).

  • models_that_fit

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

  • gpu_prices

    Cheapest on-demand price per GPU-hour from RunPod, Vast.ai, Verda and Azure, checked every hour.