How do I install the @ruvector/ruvllm CLI skill?

Run npx skillmds@latest add ricable/ruvector-ruvllm-cli in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is @ruvector/ruvllm CLI safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with @ruvector/ruvllm CLI?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is @ruvector/ruvllm CLI free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published @ruvector/ruvllm CLI?

ricable (@ricable) published this skill. Their other Agent Skills are listed on their SkillMD profile.

@ruvector/ruvllm CLI by ricable — Agent Skill

Name: @ruvector/ruvllm CLI
Rating: 4.2 (5 reviews)
Author: ricable

@ruvector/ruvllm CLI

CLI for local LLM inference with Metal/CUDA acceleration, model management, and benchmarking. Use when running local LLM inference, downloading and managing GGUF models, benchmarking inference performance, serving models via HTTP API, or comparing model outputs across different quantization levels.

ricable Updated Sep 10, 2026

File contents

@ruvector/ruvllm-cli

CLI for local LLM inference, benchmarking, and model management. Run quantized models locally with Metal (macOS) and CUDA (Linux/Windows) GPU acceleration. Supports GGUF format models, HTTP serving, and performance benchmarking.

Quick Command Reference

Task	Command
Show help	`npx @ruvector/ruvllm-cli@latest --help`
Run inference	`npx @ruvector/ruvllm-cli@latest run --model <path>`
Chat mode	`npx @ruvector/ruvllm-cli@latest chat --model <path>`
Download model	`npx @ruvector/ruvllm-cli@latest download <model-id>`
List models	`npx @ruvector/ruvllm-cli@latest models list`
Serve model	`npx @ruvector/ruvllm-cli@latest serve --model <path>`
Benchmark	`npx @ruvector/ruvllm-cli@latest bench --model <path>`
Model info	`npx @ruvector/ruvllm-cli@latest info <model-path>`

Installation

Install: npx @ruvector/ruvllm-cli@latest See Installation Guide for the full ecosystem.

Core Commands

run

Run inference on a prompt.

npx @ruvector/ruvllm-cli@latest run --model <path> --prompt "Your prompt"

Options: --model <path>, --prompt <text>, --max-tokens <n>, --temperature <f>, --gpu, --threads <n>

chat

Interactive chat mode.

npx @ruvector/ruvllm-cli@latest chat --model <path>

Options: --model <path>, --system <prompt>, --temperature <f>, --gpu

download

Download models from Hugging Face Hub.

npx @ruvector/ruvllm-cli@latest download <model-id> [--quantization q4_k_m]

models

Model management.

npx @ruvector/ruvllm-cli@latest models list
npx @ruvector/ruvllm-cli@latest models info <name>
npx @ruvector/ruvllm-cli@latest models delete <name>

serve

Serve model via HTTP API (OpenAI-compatible).

npx @ruvector/ruvllm-cli@latest serve --model <path> --port 8080

bench

Benchmark inference performance.

npx @ruvector/ruvllm-cli@latest bench --model <path> [--iterations <n>]

Common Patterns

Quick Chat

npx @ruvector/ruvllm-cli@latest download TheBloke/Llama-2-7B-GGUF --quantization q4_k_m
npx @ruvector/ruvllm-cli@latest chat --model llama-2-7b-q4_k_m.gguf --gpu

API Server

npx @ruvector/ruvllm-cli@latest serve --model ./model.gguf --port 8080 --gpu
# Then: curl http://localhost:8080/v1/chat/completions -d '{"messages": [...]}'

RAN DDD Context

Bounded Context: Learning

References

Command reference: See references/commands.md
Full README
npm

---name: ruvector-ruvllm-clidescription: CLI for local LLM inference with Metal/CUDA acceleration, model management, and benchmarking. Use when running local LLM inference, downloading and managing GGUF models, benchmarking inference performance, serving models via HTTP API, or comparing model outputs across different quantization levels.---# @ruvector/ruvllm-cliCLI for local LLM inference, benchmarking, and model management. Run quantized models locally with Metal (macOS) and CUDA (Linux/Windows) GPU acceleration. Supports GGUF format models, HTTP serving, and performance benchmarking.## Quick Command Reference| Task | Command ||------|---------|| Show help | `npx @ruvector/ruvllm-cli@latest --help` || Run inference | `npx @ruvector/ruvllm-cli@latest run --model <path>` || Chat mode | `npx @ruvector/ruvllm-cli@latest chat --model <path>` || Download model | `npx @ruvector/ruvllm-cli@latest download <model-id>` || List models | `npx @ruvector/ruvllm-cli@latest models list` || Serve model | `npx @ruvector/ruvllm-cli@latest serve --model <path>` || Benchmark | `npx @ruvector/ruvllm-cli@latest bench --model <path>` || Model info | `npx @ruvector/ruvllm-cli@latest info <model-path>` |## Installation**Install**: `npx @ruvector/ruvllm-cli@latest`See [Installation Guide](../_shared/installation-guide.md) for the full ecosystem.## Core Commands### runRun inference on a prompt.```bashnpx @ruvector/ruvllm-cli@latest run --model <path> --prompt "Your prompt"```**Options:** `--model <path>`, `--prompt <text>`, `--max-tokens <n>`, `--temperature <f>`, `--gpu`, `--threads <n>`### chatInteractive chat mode.```bashnpx @ruvector/ruvllm-cli@latest chat --model <path>```**Options:** `--model <path>`, `--system <prompt>`, `--temperature <f>`, `--gpu`### downloadDownload models from Hugging Face Hub.```bashnpx @ruvector/ruvllm-cli@latest download <model-id> [--quantization q4_k_m]```### modelsModel management.```bashnpx @ruvector/ruvllm-cli@latest models listnpx @ruvector/ruvllm-cli@latest models info <name>npx @ruvector/ruvllm-cli@latest models delete <name>```### serveServe model via HTTP API (OpenAI-compatible).```bashnpx @ruvector/ruvllm-cli@latest serve --model <path> --port 8080```### benchBenchmark inference performance.```bashnpx @ruvector/ruvllm-cli@latest bench --model <path> [--iterations <n>]```## Common Patterns### Quick Chat```bashnpx @ruvector/ruvllm-cli@latest download TheBloke/Llama-2-7B-GGUF --quantization q4_k_mnpx @ruvector/ruvllm-cli@latest chat --model llama-2-7b-q4_k_m.gguf --gpu```### API Server```bashnpx @ruvector/ruvllm-cli@latest serve --model ./model.gguf --port 8080 --gpu# Then: curl http://localhost:8080/v1/chat/completions -d '{"messages": [...]}'```## RAN DDD Context**Bounded Context**: Learning## References- **Command reference**: See [references/commands.md](references/commands.md)- [Full README](references/npm-readme.md)- [npm](https://www.npmjs.com/package/@ruvector/ruvllm-cli)

Frequently asked questions