• Black nvidia rtx pro 6000 graphics card with 96gb gddr7 ecc and angular design featuring textured speaker grilles
  • Green and white stylized nvidia eye logo above bold black letters on hpe s6a73c rtx pro 6000 blackwell 96gb gpu
1 2

HPE

HPE S6A73C | RTX PRO 6000 Blackwell 96GB PCIe Gen5 GPU, Passive, 600W

S6A73C

Stock Status: Enquire

Request Quote
Sale Sold out
Shipping calculated at checkout.
20-min response

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

Description

The NVIDIA RTX PRO 6000 Blackwell Server Edition is a 96GB GDDR7 ECC PCIe Gen5 GPU accelerator for HPE ProLiant servers. Built on the Blackwell architecture with 24,064 CUDA cores and fifth-generation Tensor Cores, it suits enterprise AI, scientific computing, rendering, 3D graphics and video workloads. This 600W, passively cooled dual-slot model is designed for multi-GPU server deployments and supports Multi-Instance GPU partitioning.

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

Features

- Fifth-generation Tensor Cores with FP4 precision support
- Fourth-generation ray-tracing cores
- 96GB GDDR7 for agentic AI, physical AI, scientific computing, rendering, 3D graphics and video
- Multi-Instance GPU support for isolated GPU partitions
- Confidential Compute and Secure Boot with Root of Trust supported
- Managed through HPE iLO with HPE Silicon Root of Trust
- Passive cooling design for multi-GPU server deployments

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

Technical Specifications

FAQs

Technical Specifications

- Part number S6A73C (NVIDIA board 2G153)
- NVIDIA Blackwell architecture
- 96 GB GDDR7 with ECC, 512-bit memory interface
- Memory bandwidth 1597 GB/s
- 24,064 CUDA cores
- 752 5th-gen Tensor Cores
- 188 4th-gen RT Cores
- FP32 120 TFLOPS, peak FP4 AI 4 PFLOPS, peak RT core performance 355 TFLOPS
- PCIe Gen 5 x16 host interface
- Max power up to 600W (configurable 400-600W)
- Passive thermal solution
- Form factor: FHFL dual slot, 4.4in H x 10.5in L
- 4x DisplayPort 2.1 (typically disabled by default in server configurations)
- Multi-Instance GPU: up to 4 MIGs at 24GB
- 4x NVENC (9th gen), 4x NVDEC (6th gen)
- Power connector: 1x PCIe CEM5 16-pin

FAQs

Q: Which HPE servers is this accelerator compatible with?
A: It is compatible with HPE ProLiant DL380a Gen12 and DL385 Gen11 servers.

Q: How is this GPU cooled?
A: It uses a passive thermal solution and relies on server chassis airflow, making it suited to multi-GPU rack server deployments.

Q: What power connection does it require?
A: It uses a single PCIe CEM5 16-pin power connector, with maximum power up to 600W and a configurable range of 400-600W.

Q: Does it support GPU partitioning?
A: Yes. Multi-Instance GPU is supported, allowing up to 4 isolated MIG instances of 24GB each.

Q: What workloads is it designed for?
A: It targets enterprise AI, scientific computing, rendering, 3D graphics and video workloads, using 96GB of GDDR7 ECC memory, fifth-generation Tensor Cores and fourth-generation RT Cores.

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