Private AI servers

Run your team's AI assistant and models on a rack server you own. Prompts and documents stay on your network.

Runs vLLM · Open WebUI · Ollama

  • From $34,999
  • GPU memory 32–192 GB
  • Ships in 7–10 business days
Novatech AI server in a SilverStone RM600 6U rackmount chassis

Which models fit

Model 32 GBRTX 5090From $34,999 96 GBRTX PRO 6000From $73,999 192 GB2× RTX PRO 6000From $92,998
gpt-oss-20bOpenAI · 21BFitsFitsFits
Qwen3 32BAlibaba · 32B4-bitFullFull
Llama 3.3 70BMeta · 70BDoesn't fit in GPU memory8-bitFull
gpt-oss-120bOpenAI · 117BDoesn't fit in GPU memoryFitsFits
Qwen3 235B-A22BAlibaba · 235BDoesn't fit in GPU memoryDoesn't fit in GPU memory4-bit
  • Full16-bit, full quality
  • FitsRuns as released
  • 8-bitCompressed, close to full quality
  • 4-bitCompressed, small quality drop
  • Doesn't fit in GPU memory

Approximate GPU memory for the model plus a working context. Full means 16-bit. On two-GPU servers, vLLM splits one model across both cards.

Check any model in the Build Finder

Every build comes with

  • Ready on first bootWindows 11 Pro or Ubuntu. Ollama, Open WebUI or ComfyUI set up on request.
  • 48-hour burn-in report
  • 3-year limited warranty
  • Lifetime technical support
  • Assembled in USA from new parts
  • Built in 7–10 business days, shipped free
How many people can use it at once?

It depends on the model, how long the prompts are and how many arrive at the same moment. vLLM batches requests so many people can share one GPU. Tell us your team size and model, and we'll test it on the server before it ships.

How is a server different from a workstation?

A server goes in a rack and runs around the clock for many users, with remote management (IPMI) and two 10 Gb Ethernet ports. A workstation sits under one person's desk.

Which models can it run?

Open models like Llama, Qwen, DeepSeek and gpt-oss. The two-GPU servers hold 192 GB, enough for Llama 3.3 70B at full precision or Qwen3 235B at 4-bit.

Does any data leave our network?

Not unless you set it up to. The models run on the server's own GPUs, so prompts and documents stay on your network, and it works with no internet connection once the models are downloaded.

Does it come set up?

Yes. It ships with Windows 11 Pro, or Ubuntu if you ask, and we can set up Ollama with Open WebUI before it ships so your team can sign in on day one.

Your AI systems expert

  • POs and purchase cards welcome
  • Net terms
  • University & government procurement
Liquid-cooled processor and memory inside a Novatech AI server
What do you need?
What will you run?Pick all that apply.
How many people will use it?
How are you buying?Pick all that apply.
What's your budget?
Paste your specs
How many systems?
How do we reach you?
No obligation
A real engineer reviews it
Reply within 1 business day

WHAT HAPPENS NEXT

  1. An expert reads it.

    Your models, budget, and preferences, reviewed by the person who would build the system.

  2. You get a real spec.

    Configuration with pricing you can hand to procurement, in one business day.

  3. You decide.

    No obligation. If a smaller build serves your models better, that is what we recommend.