Run quantized LLMs locally with llama.cpp — CPU+GPU inference, GGUF format, OpenAI-compatible server, and Python bindings.
$npx -y skills add alexai-mcp/hermes-ccc --skill llama-cppInstalls into the current project.
Run `npx skills use "https://github.com/alexai-mcp/hermes-ccc" --skill "alexai-mcp/hermes-ccc/llama-cpp"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/alexai-mcp/hermes-ccc" that are relevant to the current task. Run `npx skills add "https://github.com/alexai-mcp/hermes-ccc"` and select the relevant skills, then follow their instructions.