Skip to main content
WerkHub AI Enterprise
Maximum scale

Enterprise

Regulated industries, large Mittelstand, multi-site. Form factor: 4U rack-mount server.

65.000 €
Custom subsidy structuring — contact for details
GPU
4× NVIDIA RTX PRO 6000 Blackwell Max-Q
VRAM
384 GB GDDR7 ECC
Users
100–500
Concurrency
50–100 simultaneous users

Full Hardware Specifications

GPU

Model4× NVIDIA RTX PRO 6000 Blackwell Max-Q
VRAM384 GB GDDR7 ECC
Bandwidth7200 GB/s
AI Performance16000 TOPS (FP4)
FP16440 TFLOPS
TDP300W per card
InterfacePCIe 5.0 x16
ArchitectureBlackwell

Processor

ModelAMD Threadripper PRO 7975WX
Cores32 / 64T
SocketsTR5
PCIe128 lanes

Memory

Capacity512 GB
TypeDDR5 ECC
Configuration8×64 GB

Storage

Capacity8 TB
TypeNVMe Gen4
Configuration2×4 TB NVMe (RAID 1)

Platform

Form Factor4U rack-mount server
MotherboardASUS WRX90E-SAGE (TRX50 / WRX90)
Power Supply2000W 80+ Titanium
NetworkIntel X550-T2 (Dual 10GbE)

AI Performance

Max Model (FP16)120B+ (tensor parallel)
Max Model (Quantized)400B+ (Q4) / multiple concurrent 70B
Concurrency50–100 simultaneous users
Power Consumption1800W

Pre-loaded AI Models

Every appliance ships with a curated selection of production-ready open-source models. Swap or add models anytime.

Llama 4 Scout
Llama 4 Scout
17B · FP16
Gemma 4 31B
Gemma 4 31B
31B · FP16
Qwen 3.6 35B
Qwen 3.6 35B
35B · FP16
GLM-4.7 30B
GLM-4.7 30B
30B · FP16
Mistral Small 3.1
Mistral Small 3.1
24B · FP16
Devstral 2 24B
Devstral 2 24B
24B · FP16
Devstral 2 123B
Devstral 2 123B
123B · Q4
Qwen3-Coder-Next 80B
Qwen3-Coder-Next 80B
80B · Q8
Nemotron 3 Super 120B
Nemotron 3 Super 120B
120B · Q4

AI-Powered Applications

Run agentic coding tools and automation platforms locally — with full data privacy. No API keys, no cloud dependency.

Claude Code
Claude Code
Codex
Codex
OpenCode
OpenCode
OpenClaw
OpenClaw

What's included with this tier

Every WerkHub AI appliance ships ready to run. No extra setup fees, no surprise add-ons — software, installation, and support are all in the price.

Software stack

Full AI software stack pre-installed (vLLM, Open WebUI, WerkHub Console, multi-model tensor-parallel config, monitoring, audit logging)

Installation & onboarding

Delivery + on-site rack integration + network setup + compliance documentation + multi-day staff training

Support

24/7 priority support, 12 months included. Dedicated account engineer, proactive monitoring, guaranteed SLA response, on-site hardware replacement.

Alternative GPU Configurations

This appliance is also available with AMD or Intel GPUs at different price points. Contact us for details.

AMDProven
GPU8× Radeon AI PRO R9700
VRAM256 GB GDDR6
Bandwidth5120 GB/s
Price38.000 €

256 GB total across 8 GPUs. Excellent throughput. Multi-chassis may be needed for 8-card deployments.

Ready to get started?

Request a quote for this configuration or book a consultation to discuss your specific needs.

Request a Quote