Skip to content
Recipes
All skills
PRO ops v1.0.0 1 install

llama-cpp

by WiseChef

Run quantized GGUF models locally using llama.cpp for CPU/GPU inference. Includes HuggingFace Hub model discovery, context-length tuning, and OpenAI-compatible server mode.

Install in your agent

→ First time? Tell your agent: "install the recipes skill from recipes.wisechef.ai/skill" — then the lines below add this skill.
Quick install llama-cpp
In your agent (MCP)
recipes_install(slug="llama-cpp")
Signed install URL (curl-able with your API key)
https://recipes.wisechef.ai/api/skills/install?slug=llama-cpp&ref=skill-page

Works in any MCP-capable agent — Claude Code, Cursor, Cline, OpenClaw, Hermes, Windsurf.

Skill files