skills.rest
nadicodeai
nadicodeaiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

llama-cpp

Run local GGUF model inference and discover models on HF Hub with llama.cpp.

Updated Apr 9, 2026
Search Tags:#quantization#inference#model-discovery#gguf#llama.cpp#hugging-face
One-click install
npx skills add https://github.com/nadicodeai/argo-agent --skill llama-cpp-nadicodeai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llama-cpp
Source: https://github.com/nadicodeai/argo-agent/tree/main/skills/mlops/inference/llama-cpp
Command: npx skills add https://github.com/nadicodeai/argo-agent --skill llama-cpp-nadicodeai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

llama.cpp enables local GGUF inference and HF Hub-based model discovery, removing the need to rely on external APIs for basic AI tasks.

Core Features & Use Cases

  • Local GGUF inference across CPU and GPU backends, including Apple Silicon.
  • HF Hub model discovery and quick quantization guidance for GGUF files.
  • Simple workflows to deploy a local server or CLI for offline inference.

Quick Start

Install llama.cpp and begin discovering GGUF models on HF Hub, then run a local server or CLI for inference.

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 without external API dependencies?▼

Local GGUF inference is enabled by using llama.cpp to run models directly on your machine. It supports Linux, macOS, and Windows environments across CPU, Apple Silicon, and GPU offload backends for offline deployment.

How do I discover and select GGUF models from Hugging Face Hub for local inference?▼

Hugging Face Hub model discovery is integrated directly into the workflow to help you find and select GGUF files. It provides quick quantization guidance to prepare models for local inference and offline deployment.

Can I use llama.cpp for inference on Apple Silicon and GPU offload workflows?▼

llama.cpp supports Apple Silicon and GPU offload workflows for local GGUF inference. It applies to Linux, macOS, and Windows environments, allowing hardware acceleration across CPU and GPU backends.

What's the best way to deploy a local offline inference server or CLI using GGUF models?▼

Deploying a local offline inference server or CLI is achieved through simple llama.cpp workflows. The process coordinates local inference, HF Hub model selection, and optional scripts to run a local server.

Does this workflow provide guidance for model quantization when working with GGUF files?▼

Quick quantization guidance for GGUF files is a core feature of this workflow. It assists with preparing models discovered on Hugging Face Hub for local inference across various hardware backends.

Related Skills

Explore More Software Engineering Skills→
evalstateevalstate

trl

Submit TRL training jobs on Hugging Face Jobs and convert models to GGUF.

Community
Advanced
afel6afel6

llama-cpp

Run GGUF-quantized LLM inference on CPUs and non-NVIDIA GPUs.

Community
Advanced
EskyeeEskyee
14

blueagent-x402

Run security checks on Base transactions with quantum vulnerability assessment.

Community
Advanced
attentiondotnetattentiondotnet

llama-cpp

Run LLM inference on CPU, Apple Silicon, and non-NVIDIA GPUs with GGUF quantization.

Community
Advanced