24.11.2025
GPT-OSS 120B on AI Cube Pro: Run OpenAI's Open-Source Model Locally
With GPT-OSS 120B, OpenAI released their first open-weight model since GPT-2 in August 2025 – and it's impressive. The model achieves near o4-mini performance but...

Professional installation on your infrastructure – on-premise, cloud or hybrid
On-Premise
In your data center
Cloud Installation
AWS, Azure, Hetzner & more
Security Setup
VPN, SSO, Hardening
Professional installation where you need it
Installation on your own hardware in your data center or server room
Installation on your cloud infrastructure at AWS, Azure, Google Cloud or Hetzner
High-availability setup with comprehensive security and compliance features
Secure access and access control for your installation
WireGuard, NetBird or Tailscale
Keycloak, Authentik, Azure AD
TOTP, WebAuthn, YubiKey
Fail2Ban, Rate Limiting, IP Whitelisting
We set up secure VPN access to your installation – ideal for remote work and external employees.
Chatten Sie mit Ihren Unternehmens dokumenten: PDFs, Word-Dateien, Präsentationen und mehr
Private LLM-Nutzung für DSGVO-kritische Unternehmen und Behörden mit vollständiger Datenkontrolle
Nutzen Sie Ollama, OpenAI, Claude, Gemini und mehr in einer Plattform mit Workspace-Management
Implementieren Sie Retrieval-Augmented Generation für präzise, kontextbezogene Antworten
Automatisieren Sie Kundenanfragen mit AI Agents, die aus Ihrer Wissensdatenbank lernen
Betreiben Sie LLMs komplett lokal mit Ollama ohne externe API-Abhängigkeiten
Full-service installation with no hidden costs
Expertise that moves you forward
We have successfully implemented dozens of enterprise installations and know all best practices.
Comprehensive security hardening following OWASP, including VPN access, firewall configuration and audit logging.
We rely on open-source software and avoid vendor lock-in – you retain full control over your data.
Whether AWS, Azure, Google Cloud, Hetzner or on-premise – we install where you need it.
You get a dedicated contact person who supports you during and after installation.
Your installation runs on your infrastructure – you are always independent and can continue operating the solution yourself.
Good choice – we'll help you get started or with operations.
Discover all features, use cases and managed hosting options for AnythingLLM
Go to AnythingLLM Overview24.11.2025
With GPT-OSS 120B, OpenAI released their first open-weight model since GPT-2 in August 2025 – and it's impressive. The model achieves near o4-mini performance but...
09.11.2025
In times of rising cloud costs, data sovereignty challenges and vendor lock-in, the topic of local AI inference is becoming increasingly important for companies. With...
08.11.2025
The use of Large Language Models (LLMs) such as GPT-4, Claude or Llama has evolved from experimental applications to mission-critical tools in recent years. However,...
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.
Timo Wevelsiep & Robin Zins
CEOs of WZ-IT

