Skip to main content
Glama

StudioTV LLM VRAM Calculator

Server Details

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

If you are the author of this connector, you can claim ownership. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.6/5.0

Scored across 3 tools

Disambiguation4/5

The three tools target distinct queries: forward estimation for a specific model (estimate_vram), raw price lookup per GPU (gpu_prices), and reverse lookup of models that fit given hardware (models_that_fit). estimate_vram and models_that_fit share the VRAM-fitting concept, but the direction of the query is clearly opposite, so misselection risk is low.

Naming Consistency4/5

All names are snake_case and readable, but the pattern is mixed: estimate_vram is verb_noun while gpu_prices and models_that_fit are noun phrases. This is a minor deviation rather than a confusing one, since each name still conveys its action clearly.

Tool Count4/5

Three tools is lean but well-matched to a narrow domain (VRAM and cost estimation for open LLMs); each tool serves a distinct, necessary purpose. It is on the thin side — no tool for quantization or fine-tuning estimates — but not a mismatch.

Completeness4/5

The surface covers the core lifecycle: estimate resources for a model, list GPUs with prices, and find models fitting given hardware. Minor gaps exist, such as no explicit control over context length, batch size, or throughput benchmarking, but agents can work around these via tool parameters or external reasoning.

Available Tools

3 tools
estimate_vramDoes this LLM fit on this GPU?B
Read-only
Inspect

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).

Inputs: model (required), gpu, engine, context, +4 more.

gpu_pricesGPU rental pricesA
Read-only
Inspect

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.

Inputs: gpu.

models_that_fitWhich LLMs fit on this GPU?A
Read-only
Inspect

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

Inputs: gpu (required), engine, context, weights, +3 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      LLM deployment planner: given a model and a GPU, answers will it fit, will it hit your SLO, and what will it cost. Sizes VRAM and KV-cache from the model's real architecture, and labels every number measured, estimated, or unknown.
      5
      1,118 PyPI
      3
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Checks whether an open-weight LLM fits your GPU: VRAM for weights, KV cache and overhead at each quantisation, a tokens-per-second ceiling, the longest context that fits, and what would work instead when it doesn't. Reads any Hugging Face repo's config.json. Free, read-only, no API key.
      6
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources