skills.rest
ricable
ricableCOMMUNITY
Explore all skills by this author →
GitHub

@ruvector/ruvllm-cli

Run local GGUF model inference with Metal and CUDA acceleration.

1|Updated Feb 8, 2026
Search Tags:#llm#benchmarking#model management#gguf#local inference#gpu acceleration
One-click install
npx skills add https://github.com/ricable/cli-skills-builder --skill ruvector-ruvllm-cli
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: @ruvector/ruvllm-cli
Source: https://github.com/ricable/cli-skills-builder/tree/main/.claude/skills/ruvector-ruvllm-cli
Command: npx skills add https://github.com/ricable/cli-skills-builder --skill ruvector-ruvllm-cli

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill simplifies running and managing Large Language Models (LLMs) locally on your own hardware, enabling powerful AI capabilities without relying on cloud services.

Core Features & Use Cases

  • Local LLM Inference: Run LLMs directly on your machine with GPU acceleration (Metal/CUDA).
  • Model Management: Download, list, and manage GGUF model files.
  • Benchmarking: Measure the performance of your local LLM setup.
  • Use Case: You need to experiment with different open-source LLMs for a specific task, but want to keep your data private and avoid API costs. This Skill allows you to download, test, and serve models locally.

Quick Start

Download the 'TheBloke/Llama-2-7B-GGUF' model with q4_k_m quantization and then start an interactive chat session.

Frequently Asked Questions about @ruvector/ruvllm-cli

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

FAQPage Schema
How do I run local LLM inference using GGUF models on my own hardware?▼

To run local LLM inference with GGUF models, you can utilize this tool to execute commands via npx, enabling direct deployment on your machine with Metal or CUDA GPU acceleration.

How do I download and manage GGUF model files from Hugging Face?▼

You can download and manage GGUF model files from Hugging Face by using the built-in model management features to fetch specific models and quantizations, then list and organize them locally.

Can I benchmark local inference performance for Large Language Models?▼

Yes, you can benchmark local inference performance for Large Language Models by using the integrated benchmarking feature to measure and compare execution speeds on your hardware setup.

Does local LLM inference work with both Metal and CUDA GPU acceleration?▼

Local LLM inference supports both Metal and CUDA GPU acceleration, allowing you to leverage native hardware capabilities to run Large Language Models efficiently without cloud services.

How do I serve a local LLM via an HTTP API for application integration?▼

You can serve a local LLM via an HTTP API by utilizing the serving functionality, which exposes your downloaded GGUF models over HTTP for seamless integration with other applications.

Related Skills

Explore More Software Engineering Skills→
nishide-devnishide-dev

tool-pixi

Manage reproducible ML Python environments with Pixi and pixi.lock.

Community
Intermediate
surus-latsurus-lat
8

evaluate

Executes standardized AI benchmarking workflows with smoke tests and configurable interfaces.

Official
Advanced
evalstateevalstate

trl

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

Community
Advanced
helix4uhelix4u

llama-cpp

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

Community
Intermediate