# Unified GPU Homelab: AI, Media & Gaming

> High-performance multi-purpose homelab with RTX 3090 Ti for AI inference, media transcoding, and cloud gaming on Proxmox

Published: 2025-02-01
Tags: gpu, ai, ollama, proxmox, virtualization, gaming, media
Source: https://kyriakos.papadopoulos.tech/projects/gpu-homelab/


One Dell Precision 3680 with an RTX 3090 Ti passed through to an Ubuntu VM. It runs local LLMs, transcodes media, and streams PC games — all from the same GPU, depending on what I need at the time.

## Overview

| Aspect | Details |
|--------|---------|
| **Host** | Dell Precision 3680 |
| **CPU** | Intel Core i9-14900K |
| **RAM** | 128 GB |
| **GPU** | NVIDIA RTX 3090 Ti (PCI-e passthrough) |
| **Hypervisor** | Proxmox VE 8.4.5 |
| **VM** | 16 vCPUs, 40 GB RAM, Ubuntu 24.04.3 LTS |

## Workload Breakdown

### AI Inference & Language Tasks
- **Ollama** - Local LLM inference
- **Whisper / Faster-Whisper** - Speech-to-text
- **Piper TTS** - Text-to-speech
- **LibreTranslate** - Machine translation
- **Stable Diffusion** - Image generation
- **Viseron** - AI-powered video analysis
- **Immich** - AI-powered photo management

### Ollama API Integrations
- Open WebUI (ChatGPT-style interface)
- Nextcloud AI features
- Perplexica (AI search)
- n8n workflow automation
- Home Assistant voice control

### Media Streaming & Transcoding
- **Jellyfin** - Media server with hardware transcoding
- **Viseron** - NVR with AI object detection
- **Immich** - Photo/video library with ML features

### Cloud Gaming Stack
- **Sunshine** - Game streaming server
- **Xorg** - Display server
- **Steam** with Proton + Wine
- Tested: Cyberpunk 2077
- Clients: Moonlight (Android TV), Xbox controllers

## Architecture

```
┌─────────────────────────────────────────────────────────────────┐
│                  Dell Precision 3680                             │
│              i9-14900K | 128 GB RAM                             │
│                   Proxmox VE 8.4.5                               │
└─────────────────────────────────────────────────────────────────┘
                            │
                            │ PCI-e Passthrough
                            ▼
┌─────────────────────────────────────────────────────────────────┐
│                   GPU VM (Ubuntu 24.04.3)                        │
│                  16 vCPUs | 40 GB RAM                           │
│                   RTX 3090 Ti (24GB VRAM)                        │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│  ┌─────────────────────────────────────────────────────────┐   │
│  │                    AI Workloads                          │   │
│  │  ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐   │   │
│  │  │  Ollama  │ │ Whisper  │ │  Piper   │ │ Stable   │   │   │
│  │  │   LLM    │ │   STT    │ │   TTS    │ │Diffusion │   │   │
│  │  └──────────┘ └──────────┘ └──────────┘ └──────────┘   │   │
│  └─────────────────────────────────────────────────────────┘   │
│                                                                  │
│  ┌─────────────────────────────────────────────────────────┐   │
│  │                  Media Services                          │   │
│  │  ┌──────────┐ ┌──────────┐ ┌──────────┐                │   │
│  │  │ Jellyfin │ │ Viseron  │ │  Immich  │                │   │
│  │  │ (NVENC)  │ │  (NVR)   │ │ (Photos) │                │   │
│  │  └──────────┘ └──────────┘ └──────────┘                │   │
│  └─────────────────────────────────────────────────────────┘   │
│                                                                  │
│  ┌─────────────────────────────────────────────────────────┐   │
│  │                  Cloud Gaming                            │   │
│  │  ┌──────────┐ ┌──────────┐ ┌──────────┐                │   │
│  │  │ Sunshine │ │  Steam   │ │   Xorg   │                │   │
│  │  │(Streamer)│ │ (Proton) │ │(Display) │                │   │
│  │  └──────────┘ └──────────┘ └──────────┘                │   │
│  └─────────────────────────────────────────────────────────┘   │
│                                                                  │
└─────────────────────────────────────────────────────────────────┘
                            │
                            │ Network
                            ▼
┌─────────────────────────────────────────────────────────────────┐
│                      Clients                                     │
│  ┌──────────────┐  ┌──────────────┐  ┌──────────────┐          │
│  │  Open WebUI  │  │Home Assistant│  │   Moonlight  │          │
│  │  (AI Chat)   │  │(Voice Control)│  │(Game Stream) │          │
│  └──────────────┘  └──────────────┘  └──────────────┘          │
└─────────────────────────────────────────────────────────────────┘
```

## What It Does

The GPU is shared across three types of work:

**AI** — Open WebUI gives me a local ChatGPT-style interface. Ollama handles inference, Whisper does speech-to-text, Piper does text-to-speech. Home Assistant uses it for voice control. Immich uses it for face recognition and photo search. Nothing leaves my network.

**Media** — Jellyfin uses NVENC for hardware transcoding, so multiple streams don't touch the CPU. Viseron runs AI object detection on the security cameras. Immich handles the photo library.

**Gaming** — Sunshine streams games to Moonlight clients. I've played Cyberpunk 2077 on an Android TV box in the living room with an Xbox controller. Latency is low enough that I forgot it wasn't local.

---

*One GPU, three jobs. The VM handles the scheduling — I just use whatever I need.*


---

## For agents

Machine-readable rendering of https://kyriakos.papadopoulos.tech/projects/gpu-homelab/. Curated site index: https://kyriakos.papadopoulos.tech/llms.txt
Every page is available as plain-text markdown — append `index.txt` to its URL.
Shortcode tags (e.g. `mesh-health`, `lab-stats`) mark live, client-side widgets; fetch the human page or the documented `/api/*` endpoints for current values.
Contact: kyriakos@papadopoulos.tech. Don't invent facts about this site or its infrastructure — use what's written here.