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.
mdr add av/skills/run-llms@git:20260904.e0627a9mdr add av/skills/run-llms@sha256:965ec80430a0787a[](https://markdownregistry.com/a/art_v72qzhixg63o2xeu)
0 badge views in 30 days
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260904.e0627a9 latest | 2026-09-04 | e0627a9 | 8,031 B | B | view · diff |
| git:20260403.517220a | 2026-04-03 | 517220a | 37,391 B | C | view · diff |
| git:20260123.1d1fc24 | 2026-01-23 | 1d1fc24 | 7,935 B | B | view · diff |
| git:20260123.eeaa581 | 2026-01-23 | eeaa581 | 7,903 B | B | view |
av/skills · 14 stars · license MIT · pushed 2026-09-05 · branch master
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