MCP MeasureMCP Measure

índice observado

StudioTV LLM VRAM Calculator

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

¿Debería usar esto?

Calidad y seguridad

A
Calidad de la descripción
93%
Integridad del esquema
97%
Calidad de los nombres
80%
Riesgo de envenenamiento
80%
Coincidencia de permisos
100%
Cumplimiento del protocolo
100%

Hallazgos (2)

  • HIGHTool poisoning patterns detected
  • MEDIUMTool description contains URL to non-standard domainen estimate_vram

Basado en el análisis automatizado de las definiciones de herramientas y el cumplimiento del protocolo.

Costo de contexto

~877Tokens (definiciones de herramientas)
~2.2 KBTamaño de respuesta típico
Impacto moderado en la atención (0.69% del contexto de 128k)

Este es el número aproximado de tokens que se consumen cada vez que las herramientas del servidor se cargan en el contexto de un modelo. Los recuentos más altos reducen la atención disponible para otras tareas.

Instalar

Instalación con un clic

Agrega esto a tu archivo `claude_desktop_config.json`:

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

Puntos de conexión remotos

https://studiotvai.com/api/mcpstreamable-http

Qué puede hacer

Inventario de herramientas

Herramientas (3)

🟢 Solo lectura🟡 Escritura🔴 Eliminación⚪ Desconocido
🟢estimate_vram(model, gpu, gpu_count, context, concurrent_requests, ...)

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).

Esquema de entrada

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "Model name or id (\"Llama 3.3 70B\", \"qwen3.8-27b\"), Hugging Face id (\"Qwen/Qwen3-32B\") or link."
    },
    "gpu": {
      "type": "string",
      "description": "GPU id or name, e.g. \"rtx-4090\", \"H100\", \"mac-m4-max-128\". Default h100. List: https://studiotvai.com/api/gpus.json"
    },
    "gpu_count": {
      "type": [
        "integer",
        "string"
      ],
      "description": "Number of GPUs, or \"auto\" (default) for the fewest that fit."
    },
    "context": {
      "type": "integer",
      "minimum": 1,
      "description": "Tokens per request (prompt + output). Default 8192."
    },
    "concurrent_requests": {
      "type": "integer",
      "minimum": 1,
      "description": "Requests served at the same time, each with its own KV cache. Default 1."
    },
    "weights": {
      "type": "string",
      "enum": [
        "native",
        "bf16",
        "fp8",
        "int8",
        "nvfp4",
        "mxfp4",
        "int4",
        "q8_0",
        "q6_k",
        "q5_k_m",
        "q4_k_m",
        "q3_k_m",
        "fp32"
      ],
      "description": "Weight format. Default: the official checkpoint (native) or BF16."
    },
    "kv_cache": {
      "type": "string",
      "enum": [
        "bf16",
        "fp8",
        "q8_0",
        "q4_0"
      ],
      "description": "KV cache precision. Default bf16."
    },
    "engine": {
      "type": "string",
      "enum": [
        "vllm",
        "sglang",
        "trtllm",
        "llamacpp",
        "transformers"
      ],
      "description": "Serving engine. Default: vllm on data-center GPUs, llamacpp elsewhere."
    }
  },
  "required": [
    "model"
  ]
}
🟢models_that_fit(gpu, gpu_count, context, concurrent_requests, weights, ...)

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

Esquema de entrada

{
  "type": "object",
  "properties": {
    "gpu": {
      "type": "string",
      "description": "GPU id or name, e.g. \"rtx-4090\"."
    },
    "gpu_count": {
      "type": "integer",
      "minimum": 1,
      "description": "Default 1."
    },
    "context": {
      "type": "integer",
      "minimum": 1,
      "description": "Tokens per request (prompt + output). Default 8192."
    },
    "concurrent_requests": {
      "type": "integer",
      "minimum": 1,
      "description": "Requests served at the same time, each with its own KV cache. Default 1."
    },
    "weights": {
      "type": "string",
      "enum": [
        "native",
        "bf16",
        "fp8",
        "int8",
        "nvfp4",
        "mxfp4",
        "int4",
        "q8_0",
        "q6_k",
        "q5_k_m",
        "q4_k_m",
        "q3_k_m",
        "fp32"
      ],
      "description": "Weight format. Default: the official checkpoint (native) or BF16."
    },
    "kv_cache": {
      "type": "string",
      "enum": [
        "bf16",
        "fp8",
        "q8_0",
        "q4_0"
      ],
      "description": "KV cache precision. Default bf16."
    },
    "engine": {
      "type": "string",
      "enum": [
        "vllm",
        "sglang",
        "trtllm",
        "llamacpp",
        "transformers"
      ],
      "description": "Serving engine. Default: vllm on data-center GPUs, llamacpp elsewhere."
    }
  },
  "required": [
    "gpu"
  ]
}
🟢gpu_prices(gpu)

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

Esquema de entrada

{
  "type": "object",
  "properties": {
    "gpu": {
      "type": "string",
      "description": "GPU id or name. Omit for every GPU."
    }
  }
}

Comunidad

Califica este servidor

Evidencia

Observaciones recientes

verificadoversión no registrada3 herramientas