av/skills · run-llms/SKILL.md

run-llms skillB

Set up and run local LLMs with Harbor. Use when the user wants to run models locally, install Harbor, start Open WebUI, llama.cpp, Ollama, vLLM, Docker Model Runner, MLX, or oMLX, pull GGUF or HuggingFace models, add SearXNG web search, Speaches TTS/STT, or Open Terminal code execution, launch Codex/Claude/Grok/OpenCode against a Harbor backend, or troubleshoot GPU, VRAM, and service startup.

Latest version
mdr add av/skills/run-llms@git:20260904.e0627a9
Exact content
mdr add av/skills/run-llms@sha256:965ec80430a0787a
Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_v72qzhixg63o2xeu.svg)](https://markdownregistry.com/a/art_v72qzhixg63o2xeu)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260904.e0627a9 latest2026-09-04 e0627a9 8,031 BB view · diff
git:20260403.517220a2026-04-03 517220a 37,391 BC view · diff
git:20260123.1d1fc242026-01-23 1d1fc24 7,935 BB view · diff
git:20260123.eeaa5812026-01-23 eeaa581 7,903 BB view

Audit of the latest version

B  16 of 17 checks passed. Deterministic, no model, same answer every run.

Source

GitHub

av/skills · 14 stars · license MIT · pushed 2026-09-05 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_v72qzhixg63o2xeu
GET https://markdownregistry.com/api/v1/resolve?ref=av/skills/run-llms
GET https://markdownregistry.com/api/v1/blob/965ec80430a0787ac6cfe08d2092997af2ce2d6abb50cd9f9aeb779eee836330