skills.rest
Monjyu1101
Monjyu1101COMMUNITY
Explore all skills by this author →
GitHub

llama-cpp

Configure local GGUF inference and discover Hugging Face models for llama.cpp.

1|Updated Jan 31, 2026
Search Tags:#quantization#inference#huggingface#model-discovery#gguf#local-server#llama.cpp
One-click install
npx skills add https://github.com/Monjyu1101/AiDiy2026 --skill llama-cpp-monjyu1101
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llama-cpp
Source: https://github.com/Monjyu1101/AiDiy2026/tree/main/backend_hermes/skills/mlops/inference/llama-cpp
Command: npx skills add https://github.com/Monjyu1101/AiDiy2026 --skill llama-cpp-monjyu1101

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The llama-cpp skill enables local GGUF inference for llama.cpp and facilitates Hugging Face model discovery without requiring remote servers.

Core Features & Use Cases

  • Local GGUF inference on CPU, Apple Silicon, CUDA, ROCm, and Intel GPUs.
  • Quant selection and repository discovery via Hugging Face Hub for llama.cpp models.
  • Generate and run llama-server or llama-cli commands directly from HF repos or GGUF files.
  • Enumerate available GGUF files and sizes for a given repo and map them to quant labels.

Quick Start

Install and configure llama.cpp locally, then use the local-app or tree API to start a server with a chosen HF repo or GGUF file.

Frequently Asked Questions about llama-cpp

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run local GGUF inference using llama.cpp without a remote server?▼

You can run local GGUF inference by generating and executing llama-server or llama-cli commands directly from Hugging Face repositories or local GGUF files, enabling local deployment without relying on remote servers.

Can I use llama.cpp for inference on Apple Silicon and Intel GPUs?▼

Yes, llama.cpp inference is supported across CPU, Apple Silicon, CUDA, ROCm, and Intel GPUs. This allows you to deploy and run local models natively on a wide variety of hardware architectures and edge devices.

How do I find and select the right quantized model from Hugging Face for llama.cpp?▼

You can discover models by using the Hugging Face tree API to enumerate available GGUF files and sizes for a given repository. The skill maps these files to quant labels to help you select the appropriate quantization.

What's the best way to configure a local llama-server deployment from a Hugging Face repo?▼

The best way to configure a local llama-server deployment is to use the local-app or tree API to enumerate GGUF files, select a quantization level, and automatically generate the necessary server run commands directly from the chosen repository.

Do I need to manually download GGUF files before starting a local llama.cpp server?▼

You do not strictly need to manually download GGUF files beforehand. The skill facilitates repository discovery via the Hugging Face tree API and can generate commands to run the server directly from the discovered repository or file.

Related Skills

Explore More Software Engineering Skills→
fikriaffikriaf

llama-cpp

Automate discovery, download, and local inference of llama.cpp models from Hugging Face Hub.

Community
Advanced
zengbaochengzengbaocheng

llama-cpp

Run local GGUF inference with llama.cpp using llama-server or llama-cli.

Community
Advanced
jleechanorgjleechanorg

llama-cpp

Automate local GGUF inference and Hugging Face model discovery for llama.cpp.

Official
Advanced
zangjeicyzangjeicy

llama-cpp

Discover GGUF models on Hugging Face and run local llama.cpp inference.

Community
Advanced