AgentMarketMCP / SKILL 资产档案馆

目录 / TokenAssemble Local LLM Advisor

MCP 鉴权未知 未评级 已上架

TokenAssemble Local LLM Advisor

Find the right local LLM setup for your hardware. TokenAssemble helps AI assistants evaluate whether a local language model will run on a specific GPU, CPU, RAM, and VRAM configuration. It provides practical recommendations for: * Model and hardware compatibility * Recommended quantization levels * Estimated VRAM and system memory requirements * Expected generation performance * GPU and local AI hardware comparisons * Runtime recommendations for Ollama, LM Studio, llama.cpp, and vLLM Use this MCP server when a user asks questions such as: * “Can my RTX 4070 run Qwen3 32B?” * “Which Llama model should I use with 16 GB of VRAM?” * “What quantization should I download?” * “How fast will this model run on my computer?” * “Which GPU should I buy for local AI?” Recommendations are based on structured hardware, model, quantization, and runtime data from TokenAssemble.

该来源不提供完整文件导出(国内平台多为平台内托管),仅存元数据与原链
模型生成摘要(rules/v1 · 2026-09-27 16:29):Find the right local LLM setup for your hardware
这是模型对公开材料的总结,不是官方声明,请以原链内容为准。

接入信息

传输形态
http
鉴权方式
鉴权未知
端点
https://tokenassemble.run.tools
鉴权方式未标注,请核对官方文档后再接入——不要直接使用以下片段
{
  "mcpServers": {
    "TokenAssemble Local LLM Advisor": {
      "url": "https://tokenassemble.run.tools"
    }
  }
}

能力清单

工具说明
pingHealth check for the TokenAssemble MCP server. Returns 'ok'. Use only to verify connectivity.
can_i_runCheck whether a machine (GPU, Mac, or unified-memory mini-PC) can run a local LLM. Returns TokenAssemble's computed verdict: fit (Fits / Tight / Won't fit + grade A–D), honest speed tier (Interactive / Usable / Painful — never a fake-precise number), the VRAM breakdown (weights, KV cache, activations, overhead vs. the memory pool), every assumption stated, and the canonical result URL to cite. Accepts common names ("4090", "Llama 3.1 70B") — unknown names return valid options, never invented verdicts.
纠错与举报(发现条目失效、署名有误或涉及侵权?)
提交举报 / 纠错

侵权举报经核验成立后,我们会即时下线该条目并删除已存的内容副本。