Skip to product information
1 of 1

NVIDIA

NVIDIA 900-5G144-2200-000 | RTX PRO 6000 Blackwell 96GB GDDR7 ECC Graphics Card, 600W

SKU:900-5G144-2200-000

Request Quote
Sale Sold out
Shipping calculated at checkout.

Stock Status: Enquire

 Trade supply only. Server & GPU quote requests need a company name, ABN and work email address. We do not quote Gmail, Outlook or Hotmail addresses, or supply for home use. 

20-min response

Need a quote or bulk pricing? Answered within 20 minutes, Sydney business hours.

Custom Built Servers

Need a different spec, quantity or configuration?

We build configured-to-order refurbished servers from Cisco, Dell, HPE, NVIDIA Lenovo and Supermicro. Tell us what you need and we'll come back with options within 24 hours.

Configure your server now →

Description

The RTX PRO 6000 Blackwell Workstation Edition is a dual-slot, actively cooled professional graphics card built on the NVIDIA Blackwell architecture. It is aimed at AI development and local LLM fine-tuning, neural rendering, 3D design and engineering simulation, data science, high-resolution video production and large-scale VR workflows.

The card carries 96 GB of ECC GDDR7 memory on a 512-bit interface with 1792 GB/s of bandwidth, alongside 24,064 CUDA cores, fifth-generation Tensor Cores rated at 4000 AI TOPS and fourth-generation RT Cores delivering 382 TFLOPS of ray tracing performance. Single-precision performance is 126 TFLOPS. It connects over PCIe 5.0 x16 and provides four DisplayPort 2.1b outputs. Total board power is 600 W, supplied through a single PCIe CEM5 16-pin connector, so the system power supply must be able to deliver 600 W to the card.

Multi-Instance GPU support allows the 96 GB of memory to be split into up to four 24 GB instances, two 48 GB instances or a single 96 GB instance. This Workstation Edition model uses active double-flow-through cooling and fits an extended-height dual-slot space, measuring 5.4 inches high by 12 inches long.

Enquire with XS Network Tech for new or used pricing and availability.

Features

- Blackwell Streaming Multiprocessor with neural shaders that integrate neural networks inside programmable shaders
- Fifth-generation Tensor Cores with FP4 support for local LLM fine-tuning and generative AI
- Fourth-generation RT Cores with double the ray-triangle intersection rate, plus RTX Mega Geometry
- Ninth-generation NVENC and sixth-generation NVDEC with 4:2:2 encode and decode support
- 96 GB of ECC GDDR7 at 1.8 TB/s for large 3D, AI and VR datasets
- DLSS 4 with Multi Frame Generation
- DisplayPort 2.1 supporting up to 8K at 240 Hz and 16K at 60 Hz
- Universal MIG for isolated GPU instances, plus an AI Management Processor
- Double-flow-through cooling designed to sustain 600 W loads

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: Fifth generation, 4000 AI TOPS
- RT Cores: Fourth generation, 382 TFLOPS
- Single-precision performance: 126 TFLOPS
- GPU memory: 96 GB GDDR7 with ECC
- Memory interface: 512-bit
- Memory bandwidth: 1792 GB/s
- System interface: PCIe 5.0 x16
- Display connectors: 4x DisplayPort 2.1b
- Maximum simultaneous displays: more than 4x 4096 x 2160 at 120 Hz, more than 4x 5120 x 2880 at 60 Hz, more than 2x 7680 x 4320 at 60 Hz
- Video engines: 4x NVENC (ninth generation), 4x NVDEC (sixth generation)
- MIG support: up to 4x 24 GB, 2x 48 GB or 1x 96 GB
- Total board power: 600 W
- Power connector: 1x PCIe CEM5 16-pin
- Thermal solution: Active, double-flow-through
- Form factor: 5.4 in H x 12 in L, dual slot, extended height
- Graphics APIs: DirectX 12, Shader Model 6.6, OpenGL 4.63, Vulkan 1.43
- Compute APIs: CUDA 12.8, OpenCL 3.0, DirectCompute

FAQs

Q: What power connection does this card need?
A: It draws up to 600 W total board power through a single PCIe CEM5 16-pin connector. The system power supply must be able to supply 600 W to the card.

Q: What slot and space does it require?
A: It needs a PCIe 5.0 x16 slot and an extended-height dual-slot space of 5.4 inches high by 12 inches long.

Q: How is the cooling designed?
A: This Workstation Edition uses active double-flow-through cooling designed to sustain 600 W loads. It is a separate product from the passively cooled Server Edition and the lower-power Max-Q Workstation Edition.

Q: Can the GPU be partitioned into isolated instances?
A: Yes. Multi-Instance GPU support allows up to four 24 GB instances, two 48 GB instances or a single 96 GB instance.

Q: Which software APIs does it support?
A: It supports CUDA 12.8, OpenCL 3.0, DirectCompute, DirectX 12, Vulkan 1.4 and OpenGL 4.6.

  • 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