TokenMark

Measured local-LLM speeds and hardware-aware model picks for Strix Halo, DGX Spark and Mac.

GitHub · npm · Website · Registry

Dev tools & GitHub AI models & media

Downloads, last 30 days

Install

Run it directly:

npx -y @altronis/tokenmark-mcp

Or add it to your client config (Claude Desktop claude_desktop_config.json, Cursor .cursor/mcp.json):

{
  "mcpServers": {
    "tokenmark": {
      "command": "npx",
      "args": [
        "-y",
        "@altronis/tokenmark-mcp"
      ]
    }
  }
}

Generated from the package metadata in the official MCP Registry. MCP Morning does not run or test servers; check required environment variables in the project README.

Alternatives