ramalama-models(1)

✨ ramalama-models ✨

okay bestie, welcome to ramalama-models(1) — the General Commands Manual page that's about to make your whole terminal pop off. sit down, hydrate, let's get into it 💖

---

🌸 NAME 🌸

ramalama-models — list models served by a running inference server

---

🦋 SYNOPSIS 🦋

ramalama models [options]

---

💜 DESCRIPTION 💜

So like. You've got a server running. It's out there, serving models, living its best life. And you're just sitting there like… which models tho? 😭

ramalama-models is here to answer that. It lists the model identifiers that a running inference server is exposing — you know, the kind of server you'd spin up with ramalama serve. Iconic behaviour, honestly.

Here's the way it works: it queries the server's OpenAI-compatible /v1/models endpoint first. That one plays nice with llama.cpp, MLX, and basically any other OpenAI-compatible server out there. If that doesn't work out, it falls back to the llama.cpp native /models endpoint. Two options, always got a backup plan, we love a resilient queen 💅

Important vibe check: this is not the same as ramalama list. ramalama list shows you the models you've downloaded to your local storage. ramalama models is asking a server what it's got. Different things, bestie, don't mix them up 🫶

---

✨ OPTIONS ✨

• --api-key — the OpenAI-compatible API key. You can also set this in ramalama.conf, or hand it over through the RAMALAMA_API_KEY environment variable. Three ways to slide it in, pick your fave 🔑
• --help, -h — shows this help message and then dips. exit. bye 👋
• --json — prints the model list in json format, for when you want it machine-readable and lowkey gorgeous 🍓
• --url=URL — the model server URL. default is http://127.0.0.1:8080, so if you're just chilling locally you don't even have to say anything 🌈

---

🔥 EXAMPLES 🔥

List models served on the default local endpoint

$ ramalama models
tinyllama

just like that. one model, one line, no notes. ate 💅

List models from a specific server in JSON format

$ ramalama models --url http://localhost:1234 --json
["granite3-moe", "tinyllama"]

look at that clean little array. granite3-moe and tinyllama, both showing up, both thriving ✨

---

👑 SEE ALSO 👑

ramalama(1), ramalama-serve(1), ramalama-list(1)

go read those too, they're part of the family 🎀

---

📜 HISTORY 📜

Jul 2026, originally compiled by Dan Walsh dwalsh@redhat.com ⟨mailto:dwalsh@redhat.com⟩

---

and that's the whole page, bestie!! 🦋💖 thanks for reading all the way to the bottom, you're literally the main character. this was ramalama-models(1) from the General Commands Manual, dated Jul 2026 — now go list some models, you got this 🌸👑