modelread

Will this Hugging Face model run on my hardware? Fit, best quant, tok/s range, launch command.

我該用這個嗎

品質與安全性

A
說明品質
96%
結構描述完整度
90%
命名品質
80%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

根據工具定義與協定合規性的自動化分析。

上下文成本

~1,029Token(工具定義)
~1.3 KB典型回應大小
中等的注意力影響(128k 上下文的 0.80%)

這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。

安裝

一鍵安裝

將以下內容加入你的 `claude_desktop_config.json` 檔案:

{
  "mcpServers": {
    "modelread": {
      "url": "https://modelread.com/mcp"
    }
  }
}

遠端端點

https://modelread.com/mcpstreamable-http
https://patrickbdevaney-modelread-mcp.hf.space/gradio_api/mcp/streamable-http

它能做什麼

工具清單

工具(5)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
⚪modelread_mcp_estimate_fit(repo, hardware, ctx, kv_cache_dtype)

Will this Hugging Face model run on this hardware, how fast, with which quant, and with what command? Checks the repo and its quantized derivatives (GGUF / MLX / AWQ / FP8) from their real file sizes and tensor headers. Returns the best variant and alternatives, each with: verdict (fits | fits-tight | offload | no | unknown), decode and prefill tokens/sec as a calibrated range (lo/mid/hi with basis), longest context that fits, memory placement (VRAM / RAM / SSD) and an exact llama.cpp / vLLM / MLX launch command.

輸入結構描述

{
  "type": "object",
  "properties": {
    "repo": {
      "type": "string",
      "description": "Hugging Face repo id, e.g. \"Qwen/Qwen3.6-27B\" or \"unsloth/gemma-4-26B-A4B-it-GGUF\".",
      "default": "Qwen/Qwen3.6-27B"
    },
    "hardware": {
      "type": "string",
      "description": "device preset id (\"rtx4090\", \"m4max-128\", \"dgx-spark\", \"8x-h100-sxm\", \"iphone-17pro-12\"),",
      "default": "rtx4090"
    },
    "ctx": {
      "type": "integer",
      "description": "context length in tokens to fit (default 32768).",
      "default": 32768
    },
    "kv_cache_dtype": {
      "type": "string",
      "enum": [
        "f16",
        "q8_0",
        "q4_0"
      ],
      "description": "KV cache type: \"f16\", \"q8_0\" or \"q4_0\".",
      "default": "f16"
    }
  }
}
⚪modelread_mcp_compare_hardware(repo, hardware_list, ctx)

Run one Hugging Face model against several devices and rank them (best first). Use for "which of my machines should run X" or "is a 4090 or an M4 Max better for X".

輸入結構描述

{
  "type": "object",
  "properties": {
    "repo": {
      "type": "string",
      "description": "Hugging Face repo id, e.g. \"openai/gpt-oss-120b\".",
      "default": "openai/gpt-oss-120b"
    },
    "hardware_list": {
      "type": "string",
      "description": "comma-separated devices (preset ids or free text), up to 8.",
      "default": "rtx5090, m4max-128, dgx-spark, h100-sxm"
    },
    "ctx": {
      "type": "integer",
      "description": "context length in tokens (default 32768).",
      "default": 32768
    }
  }
}
🟢modelread_mcp_find_models(question, default_hardware)

Recommend open models for a task on a device, from a natural-language question. Ranks ~20k indexed Hugging Face models by fit, task benchmark percentile (vendor vs independent kept apart), quant quality and speed. Examples: "best coding model for an RTX 4090 + 64GB RAM at 32k context", "Japanese chat on a Galaxy S25 Ultra", "serve 8 users on 2x RTX 3090".

輸入結構描述

{
  "type": "object",
  "properties": {
    "question": {
      "type": "string",
      "description": "the request in plain words; name the device in it, or set default_hardware.",
      "default": "best coding model for an RTX 4090 with 64GB RAM at 32k context"
    },
    "default_hardware": {
      "type": "string",
      "description": "device used when the question names none (preset id, e.g. \"m4max-128\")."
    }
  }
}
🟢modelread_mcp_list_hardware(filter, limit)

List device presets: GPUs of every vendor, Apple Silicon, multi-GPU nodes, cloud instances (with $/hour), Jetson, phones, tablets, single-board computers and VPS tiers.

輸入結構描述

{
  "type": "object",
  "properties": {
    "filter": {
      "type": "string",
      "description": "words matched against id / name / vendor / segment, e.g. \"h100\", \"amd datacenter\", \"phone samsung\".",
      "default": "h100"
    },
    "limit": {
      "type": "integer",
      "description": "maximum rows to return.",
      "default": 40
    }
  }
}
🟢modelread_mcp_search_models(query, task, limit)

Search the modelread index of Hugging Face models by name and task (no fit estimate; fast).

輸入結構描述

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "words that must appear in the repo id, e.g. \"qwen3.6\" or \"gemma 4\".",
      "default": "gemma 4"
    },
    "task": {
      "type": "string",
      "enum": [
        "chat",
        "coding",
        "vision",
        "ocr",
        "embedding",
        "speech-to-text",
        "tts",
        "image-generation"
      ],
      "description": "chat | coding | vision | ocr | embedding | speech-to-text | tts | image-generation.",
      "default": "chat"
    },
    "limit": {
      "type": "integer",
      "description": "maximum rows (1-100).",
      "default": 20
    }
  }
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本5 個工具
已驗證未記錄版本6 個工具