Skip to product information
1 of 1

NVIDIA

NVIDIA 900-2G153-0000-000 | RTX PRO 6000 96GB GDDR7 Graphics Card, PCIe 5.0, 600W

SKU:900-2G153-0000-000

Stock Status: Enquire

$20,997.74 inc. GST
$19,088.85 ex. GST
Sale Sold out
Taxes included. Shipping calculated at checkout.

Description

The NVIDIA RTX PRO 6000 Blackwell Server Edition delivers enterprise-grade AI and graphics acceleration for data center deployments. Built on the Blackwell architecture with 24,064 CUDA cores and 96GB of GDDR7 ECC memory, this passively-cooled GPU excels at large language model inference, agentic AI, engineering simulation, 3D rendering, and scientific computing workloads. The dual-slot PCIe 5.0 form factor integrates into rack-mounted servers with four DisplayPort 2.1 outputs for visualization.

Features

NVIDIA Blackwell architecture with 24,064 CUDA cores for massive parallel processing
- 96GB GDDR7 ECC memory with 512-bit interface and 1,597 GB/s bandwidth
- Fifth-generation Tensor Cores with native FP4 precision support for AI acceleration
- Fourth-generation RT Cores delivering up to 380 TFLOPS ray tracing performance
- PCIe 5.0 x16 interface for maximum host system bandwidth
- Multi-Instance GPU (MIG) support for up to 4 GPU partitions at 24GB each
- DisplayPort 2.1 connectivity supporting up to 8K at 240Hz or 16K at 60Hz
- Ninth-generation NVENC video encoding with 4:2:2 H.264 and HEVC support
- NVIDIA Omniverse-ready for OpenUSD-based workflows and digital twin applications
- DLSS 4 with Multi Frame Generation technology
- RTX Mega Geometry technology for up to 100x more ray-traced triangles
- Passive cooling design optimized for datacenter rack-mounted servers
- 600W maximum power draw with 16-pin PCIe CEM5 connector
- Dual-slot FHFL form factor for high-density server configurations
- NVLink-ready for multi-GPU scaling in supported server platforms

Warranty

All products sold by XS Network Tech include a 12-month warranty on both new and used items. Our in-house technical team thoroughly tests used hardware prior to sale to ensure enterprise-grade reliability.

All technical data should be verified on the manufacturer data sheets.

View full details

specs-tabs

Collapsible content

Technical Specifications

FAQs

Technical Specifications

GPU Architecture: NVIDIA Blackwell
- CUDA Cores: 24,064
- Tensor Cores: 752 (5th Generation)
- RT Cores: 188 (4th Generation)
- Memory: 96GB GDDR7 with ECC
- Memory Interface: 512-bit
- Memory Bandwidth: 1,597 GB/s
- Single-Precision Performance (FP32): ~120 TFLOPS
- RT Core Performance: ~354 TFLOPS
- AI Performance (FP4): Up to 4 PFLOPS
- Host Interface: PCI Express 5.0 x16
- Display Outputs: 4x DisplayPort 2.1
- Power Consumption: Up to 600W
- Power Connector: 1x 16-pin PCIe CEM5
- Cooling: Passive (datacenter airflow required)
- Form Factor: Dual-slot FHFL
- Dimensions: 4.4 in (H) x 10.5 in (L)

FAQs

Q: What workloads is the RTX PRO 6000 Blackwell Server Edition optimized for?
A: This GPU is designed for enterprise data center workloads including large language model inference, agentic AI applications, physical AI simulation, scientific computing, engineering design, 3D rendering, video processing, and data analytics. The 96GB GDDR7 ECC memory enables processing of massive datasets and complex neural networks.

Q: What is the difference between the Server Edition and Workstation Edition?
A: The Server Edition features passive cooling designed for rack-mounted servers with forced airflow, making it suitable for multi-GPU datacenter deployments. The Workstation Edition includes active cooling for desktop workstation chassis. Both share the same Blackwell architecture, 96GB GDDR7 memory, and core specifications.

Q: Does this GPU support Multi-Instance GPU (MIG) technology?
A: Yes, the RTX PRO 6000 Blackwell Server Edition supports MIG partitioning up to 4 instances at 24GB each, allowing multiple workloads to run concurrently on a single GPU with hardware isolation and quality-of-service guarantees.

Q: What cooling requirements does the passive design require?
A: This GPU requires datacenter-grade forced airflow from server chassis fans. It cannot be used in standard tower workstations or low-airflow environments. The passive heatsink design relies on high-velocity air movement provided by rack-mounted server cooling systems.

Q: Is ECC memory supported on this card?
A: Yes, all 96GB of GDDR7 memory includes ECC (Error-Correcting Code) support, providing enhanced reliability and data integrity for mission-critical enterprise applications, scientific computing, and AI training workloads where accuracy is paramount.

Recently Viewed

  • Request a Quote

    Looking for competitive pricing? Submit a request, and our team will provide a tailored quote that fits your needs.

  • Contact Us Directly

    Have a question or need immediate assistance? Call us for expert advice and real-time support.

    Call us Now  
  • Contact Us Directly

    Have a question or need immediate assistance? Call us for expert advice and real-time support.

    Contact us