AI workstations for healthcare and life sciences

Run transcription, language models and research code on hardware inside your network, so your data stays with you.

Runs Whisper · Llama · PyTorch

  • From $28,799
  • GPU memory 96–192 GB
  • Ships in 7–10 business days
Novatech AI server in a SilverStone RM600 6U rackmount chassis

Good to know

  • Data stays on your networkModels run on the machine's own GPUs.
  • 48-hour burn-inEvery system is tested under load before it ships.
  • ECC memoryOn the Threadripper PRO builds, to catch memory errors on long jobs.
  • Rack or desk6U servers for the server room, towers for the lab.

Which models fit

Model 96 GBRTX PRO 6000From $28,799 192 GB2× RTX PRO 6000From $92,998
Llama 3.1 8BMeta · 8BFullFull
Qwen3 32BAlibaba · 32BFullFull
Llama 3.3 70BMeta · 70B8-bitFull
gpt-oss-120bOpenAI · 117BFitsFits
  • Full16-bit, full quality
  • FitsRuns as released
  • 8-bitCompressed, close to full quality

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 Model 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
Is it HIPAA compliant?

HIPAA compliance depends on how your organization sets up and runs its systems, so we don't make HIPAA claims about hardware. What we can say: the models run on the machine itself, so prompts and files aren't sent to an AI provider.

What can it run?

Speech-to-text like Whisper, open language models like Llama, Qwen and gpt-oss, and research code in PyTorch.

Does any data leave the machine?

Not to an AI provider. The models run on its own GPUs, and once they're downloaded it works with no internet connection.

Can it go in our server room?

Yes. The servers are 6U rackmount, with two 10 Gb Ethernet ports and IPMI remote management.

How do we buy?

Ask for a quote. We accept purchase orders, approved accounts can pay net 30, and we can send a W-9.

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.