# Rocinante

Heavy AI inference server.

## Hardware

| Component | Details |
|-----------|---------|
| **IP** | 10.5.1.112 |
| **GPU** | NVIDIA RTX 4090 (24 GB VRAM) |
| **Role** | Heavy AI inference (Ollama) |

## Services

### Ollama

Ollama runs on port `11434` and hosts the large-model ("heavy") tier.

| Model | Use |
|-------|-----|
| `qwen3:latest` | Fast reasoning / general chat |
| `qwen2.5:32b` | Large-context tasks |
| `gemma3:27b` | Multimodal / vision |

> **LiteLLM tier:** Rocinante is the **"heavy"** tier in LiteLLM `config.yaml`.
> Heavy-tier requests from OpenWebUI and n8n route to `http://10.5.1.112:11434`.

## Current operational note

- During Doris validation from N.O.M.A.D. on 2026-05-21, `10.5.1.112` did not answer ping and did not accept connections on `11434` or `8787`.
- Treat Rocinante-hosted Ollama heavy-tier traffic and CUDA Whisper as currently unreachable from N.O.M.A.D. until host/network reachability is restored.
- Re-validate from N.O.M.A.D. with `curl http://10.5.1.112:11434/api/tags` and `curl http://10.5.1.112:8787/health` after recovery.

## Notes

- No SSH config needed for routine use — Ollama API is accessed over LAN only
- Do not run multiple large VRAM allocations simultaneously on the 4090