LLMLab.ee

AI Workstations in Estonia

FAQ

Always-On Local Services

Homelab AI

Quiet headless systems for Ollama, Open WebUI, embeddings, and small internal AI services.

Best for

  • Always-on local inference services
  • Balanced VRAM, RAM, and storage for private tools
  • Lower noise and power focus than gaming systems

Not ideal for

  • Not a high-refresh gaming profile
  • 16GB-class GPUs still limit large models
  • Remote access and backups need planned setup

AI fit is a rough estimate; model/runtime/quantization affects results.

Homelab Inference Server

Quiet headless server for Ollama, Open WebUI, embeddings, and small internal AI services. Budget is focused on 16GB CUDA VRAM, 96GB RAM, and 4TB storage instead of oversized case or cooler spend.

GPU: NVIDIA RTX 4070 Ti SUPER

CPU: AMD Ryzen 9 7900

RAM: 96GB | Storage: 4000GB

Target: 13B-34B q4

Good for 13B-class models

Strong everyday local LLM tier; 30B may need more memory or heavier quantization.

Good for everyday local LLM use

  • Roughly suitable for: local coding assistants and 7B/8B models
  • Roughly suitable for: 13B/14B quantized models

€3,627

6 market-priced parts, 2 reference estimates

View details