Quick tech specs
- Workstation runs complex database programs efficiently, ensuring speed and consistent performance
- 1600 W power supply unit (PSU) fulfills your systems power needs for smooth and uninterrupted performance
- 4 TB SSD capacity for spacious storage and faster data transfer, ideal for large files and digital content
Know your gear
Overview | Shareable on-prem AI, built for scale.
Quickly scale and streamline AI development, inference, and agentic AI workflows with groundbreaking on-prem compute and a flexible software stack. The HP ZGX Fury AI Station hosts large-scale models up to 1 trillion parameters locally, helping keep data secure and costs predictable.
Accelerate AI development.
NVIDIA® GB300 Grace Blackwell Ultra Desktop Superchip, with 748GB of unified memory, helps speed 100Bclass AI fine-tuning on-prem.
Open, flexible tools. Fast setup. No lock-in.
Set up open-source AI tools with HP Z Toolkit and deploy models with pre-installed HP Z Runtime.
Production-grade inference. Predictable costs.
Host up to 1T parameter AI models, proprietary apps, and AI agents locally and leave token fees behind.
Shareable AI compute. Office-deployable design.
Support multiple users or dev teams on one HP ZGX Fury in a rack-mountable, office-deployable design.
Features | NVIDIA® GB10 GraceBlackwell Superchip
Get up to 1000 TOPS of AI compute at FP4 precision with an NVIDIA®Blackwell GPU. Supercharge data preprocessing and orchestration with aGrace 20-core Arm CPU.