AI Cube Pro – Premium performance for your AI infrastructure
High-end AI inference with NVIDIA RTX PRO 6000 Blackwell – perfect for large LLMs, RAG systems with millions of documents, training & fine-tuning and models up to 120B+ parameters.
230 V • 292×185×372 mm • Mini-ITX
Technical Highlights RTX PRO 6000 Blackwell
Enterprise hardware with 96 GB VRAM for maximum performance
NVIDIA RTX PRO 6000 Blackwell
96 GB GDDR7 VRAM
Sufficient for models up to 120B+ parameters
125 TFLOPS FP32
24,064 CUDA Cores
Maximum performance for large LLMs
Use cases for large LLMs and RAG systems
Internal Chatbots
Run AI assistants for customer service or internal knowledge bases – completely local and GDPR-compliant.
Code Assistance
Use models like Qwen or DeepSeek for code completion, review and documentation – without sending your codebase to the cloud.
Small to Medium Models
Llama 3.1 (7B-13B), Gemma 3, Mistral 7B, Phi-4 and many other models.
Large LLMs (70B-120B+)
Run models like Llama 3.1 70B, DeepSeek-R1 or GPT-OSS 120B completely locally.
RAG Systems
Process knowledge bases with thousands to millions of documents.
Multi-Model Operation
Run multiple models in parallel – depending on hardware configuration.
Local GPT with our AI Cube
Use Open WebUI for a ChatGPT-like experience – completely local on your own hardware
The AI Cube can be delivered with Open WebUI based on customer requirements – an intuitive, user-friendly interface that enables a local ChatGPT-like experience. No cloud dependency, no API keys, no token limits – just you and your AI models.
ChatGPT-like Interface
Familiar and intuitive user interface for natural conversations with your local AI models
Completely Local
All data and conversations stay on your hardware – no connection to external servers required
Multi-Model Support
Switch seamlessly between different AI models within the same interface
No Token Fees
Unlimited usage without pay-per-use fees or monthly API costs
Open WebUI can be pre-installed and delivered ready to use upon request. Simply plug in, power on, and immediately interact with your local AI models – like ChatGPT, but completely under your control.
Enterprise advantages with AI Cube Pro and 96 GB VRAM
Maximum Performance
125 TFLOPS and 96 GB VRAM – the most powerful Blackwell GPU for local inference.
Enterprise Data Sovereignty
Even the largest models and extensive RAG systems remain completely in your network.
Future-proof
With 96 GB VRAM you're equipped for the coming years – even for future model generations.
Production Ready
Ready to use with pre-installed software and professional support – for immediate production deployment.
Pro vs. Basic – which model fits?
Compare the two AI Cube models
AI Cube Pro
- NVIDIA RTX PRO 6000 Blackwell
- 96 GB VRAM
- Models up to 120B+ parameters
- Ideal for large LLMs, RAG & training
From €12,999.90
AI Cube Basic
- NVIDIA RTX PRO 4000 Blackwell
- 24 GB VRAM
- Models up to 13B parameters
- Ideal for chatbots & code assistance
From €3,999.90
View Basic ModelCase Study: Healthcare Facility
How a private clinic uses AI Cube Pro for medical knowledge bases
!Challenge
A network of private psychiatric clinics needed an AI solution for the central knowledge base with medical protocols, SOPs and training materials. Sensitive patient data could not go to the cloud.
✓Solution with AI Cube Pro
- RAG system with Llama 3.1 70B for complex medical queries
- Integration with BookStack as knowledge source (custom development)
- Completely local operation with managed service by WZ-IT
→Result
Immediate access to relevant protocols
Cross-location knowledge consistency
Complete GDPR compliance
Technical Specifications
| Graphics Card | NVIDIA RTX PRO 6000 Blackwell (96 GB GDDR7) |
| Network | 1 GbE (10 GbE optional) |
| Dimensions & Weight | 292×185×372 mm (H×W×D), approx. 8 kg |
| Certification | CE, RoHS, GDPR-compliant |
| Security | Secure Boot, TPM 2.0, WireGuard VPN |
Included in Delivery
Frequently Asked Questions about AI Cube Pro
Ready for enterprise AI infrastructure?
Get free consultation
Let's Talk About Your Idea
Whether a specific IT challenge or just an idea – we look forward to the exchange. In a brief conversation, we'll evaluate together if and how your project fits with WZ-IT.
Trusted by leading companies
