HP NVIDIA RTX PRO 6000 Blackwell 96GB 4DP

HP NVIDIA RTX PRO 6000 Blackwell 96GB 4DP

HP

HP NVIDIA RTX PRO 6000 Blackwell 96GB 4DP graphics card

The HP NVIDIA RTX PRO 6000 Blackwell 96GB 4DP is the first professional workstation GPU built on the NVIDIA Blackwell architecture, delivering 96GB of ultra-fast GDDR7 memory with a throughput of 1792GB/s, 24064 CUDA cores, 5th-generation Tensor Cores with FP4 support, and 3511 TOPS of AI performance – all in a dual-slot, full-height design with a 300W TBP optimised for configurations of up to four GPUs in a single system. For researchers, AI developers, VFX professionals, and data scientists who need to invest in infrastructure ready for the next decade, the RTX PRO 6000 Blackwell Max-Q is the only answer.

Nvidia GeForce RTX 40

GDDR7 / 96GB

Operating memory
NVIDIA GPU

PCIe 5.0 x16

Bus interface
NVIDIA GPU

1× PCIe CEM5 16-pin

Additional power
Nvidia GeForce RTX 40

Blackwell (GB202)

Chip architecture
Nvidia GeForce RTX 40

850W

Recommended source power
HP

Key features of the HP NVIDIA RTX PRO 6000 Blackwell 96GB 4DP graphics card

  • Features 96GB of GDDR7 ECC memory with 1792GB/s throughput on a 512-bit bus – nearly double the capacity and throughput of the previous Ada Lovelace generation for training the largest AI models, 8K VFX scenes, and extensive scientific simulations
  • NVIDIA Blackwell architecture with 24064 CUDA cores and a boost frequency up to 2288MHz, achieving 110 TFLOPS in FP32 and 333 TFLOPS of RT core performance, while new neural shaders integrate neural networks directly into programmable shaders
  • 5th-generation Tensor Cores with FP4 precision and DLSS 4 Multi-Frame Generation deliver 3511 TOPS of performance – up to three times the performance of the previous generation – and enable local LLM fine-tuning, AI model prototyping, and generative AI workflows directly on the workstation
  • 4th-generation RT Cores with 333 TFLOPS of performance bring double the ray-triangle intersection speed of the previous generation, and RTX Mega Geometry technology allows for processing up to 100× more ray-traced triangles for physically accurate scenes with billions of polygons
  • Multi-Instance GPU (MIG) enables the card to be divided into up to four fully isolated instances – configurable as 4× 24GB, 2× 48GB, or 1× 96GB – each with its own memory, cache, and compute cores for secure concurrent work by multiple users or workloads
  • Four 9th-generation NVENC video encoders and four 6th-generation NVDEC decoders with support for 4:2:2 10-bit H.264 and HEVC encoding enable real-time professional video processing for multi-cam productions, live broadcasting, and VFX workflows
  • Max-Q design with a 300W TBP and a 1× PCIe CEM5 16-pin power connector is optimised for deploying up to four GPUs in a single system, scaling the total performance to 12000 TOPS AI and 384GB of shared GDDR7 memory
  • Four DisplayPort 2.1b outputs allow for running multiple displays at resolutions up to 8K at 240Hz or 16K at 60Hz with HDR and extended colour depth for precise graphics and visualisation workflows
NVIDIA GPU

Memory that defines a new class of performance

GDDR7 memory is not just an evolution of GDDR6 – it's a fundamental change in how a GPU processes data. The HP NVIDIA RTX PRO 6000 Blackwell 96GB 4DP combines 96GB of GDDR7 ECC with a throughput of 1792GB/s on a 512-bit bus, which equates to nearly double the capacity and throughput of the previous flagship professional Ada Lovelace generation card. In practice, this means models and scenes that previously required a multi-GPU configuration or cloud infrastructure now run comfortably on a single card – and a four-card RTX PRO 6000 Blackwell Max-Q configuration will offer a total of 384GB of shared memory for the most ambitious projects.

NVIDIA GPU

A new benchmark for local AI infrastructure

3511 TOPS of performance combined with FP4 precision support in the 5th-generation Tensor Cores elevates the HP NVIDIA RTX PRO 6000 Blackwell 96GB 4DP into a category previously exclusive to data centres. The card handles local LLM fine-tuning, generative AI, training of domain-specific models, and inference of natively large networks locally, with full control over your data and no recurring cloud costs. DLSS 4 Multi-Frame Generation then adds up to three times higher frame rates in supported rendering applications and simulations, while the AI Management Processor ensures intelligent distribution of computing resources across workloads.

NVIDIA GPU

RTX Mega Geometry and neural shaders

Until now, ray tracing has been limited by the number of polygons a GPU could process in real time. 4th-generation RT Cores with RTX Mega Geometry technology push this limit an order of magnitude higher: the HP NVIDIA RTX PRO 6000 Blackwell 96GB 4DP can handle up to 100× more ray-traced triangles than the previous generation, paving the way for physically accurate scenes with billions of polygons without offline rendering. New neural shaders integrate neural networks directly into programmable shaders, so AI is no longer a post-processing layer but a natural part of the graphics pipeline. For architects, VFX artists, product designers, and researchers, this means visualisations that faithfully reflect physical reality – in real time.

Nvidia GeForce RTX 40

NVIDIA Blackwell architecture

A breakthrough generation for AI, neural rendering, and scientific computing
Nvidia GeForce RTX 40

3511 TOPS AI performance

Local LLM fine-tuning and generative AI at a data-centre level
Nvidia GeForce RTX 40

96GB GDDR7 ECC

Double the capacity and throughput compared to the previous professional generation
Nvidia GeForce RTX 40

5th generation Tensor cores

FP4 precision and DLSS 4 Multi-Frame Generation for maximum AI acceleration
Nvidia GeForce RTX 40

4th generation RT cores

RTX Mega Geometry for physically accurate scenes with billions of polygons
Nvidia GeForce RTX 40

4× DisplayPort 2.1b

Up to 8K at 240Hz or 16K at 60Hz for precise visualisation workflows
Nvidia GeForce RTX 40

Multi-Instance GPU

Securely share the power of a single card between four users or workloads
Nvidia GeForce RTX 40

Max-Q for 4-GPU setups

300W in a dense design for scalable AI infrastructure on a workstation

Specifications

Chip

Chip manufacturer NVIDIA
Model designation RTX PRO 6000
Graphics processor GB202
Chip architecture Blackwell
Number of stream processors 24,064×
Production technology 4 nm

Performance & usage

Use Professional
Card profile FHFL

Memory

VRAM capacity 96 GB
Memory type GDDR7
Bus width 512-Bit

Frequency

Core frequency 1,590 MHz
Core clock speed (Boost clock) 2,617 MHz
Memory frequency 28,000 MHz (28 GHz)
Effective memory clock (bandwidth) 28 Gbps

Interface

PC connection PCI Express x16 5.0
Bus interface PCIe 5.0 x16
Monitor connection DisplayPort 2.1b

Technology

Special graphics card features Tensor Cores

Cooling system

Cooling type Active
Cooling size Dual-slot
number of fans 2 ×

Dimensions

Width 304 mm
Height 137 mm
Depth 40 mm

Consumption

TDP 600 W
Auxiliary power supply 1x 16-pin
Recommended power sources 1,000 W

AI

Total number of TOPS 4,000
Number of TOPS (GPU) 4,000
Software platform NVIDIA CUDA
On-device AI processing GPU-accelerated AI

Tops

Total number of TOPS 4,000

AI specifications

Primary AI use LLM training
Code:  EN064p7l
Warranty: 36 months
Links: Producer's Website:
Manufacturer information

HP Inc Czech Republic s.r.o Za Brumlovkou 5/1559 140 00 Praha 4 VAT ID: CZ 03208427 Radek Mattas, [email protected]"


GO Europe GmbH, Zum Kraftwerk 1, Hattingen 45527, Germany, +49232468010, [email protected]

Hewlett-Packard was founded in the difficult times of the Great Depression. The founders were a pair of friends whose name the company still proudly bears. They started their business in an unobtrusive garage near the city of Palo Alto. It is now a national monument. HP’s success lay not in copying existing products, but in the ability and courage to come up with something new.

The first commercial triumph was an oscillator that surpassed all competition in quality, yet sold at a quarter of the price. In 1968, HP released their first desktop computer - a desktop calculator. The company currently manufactures products primarily related to computer technology - computers and laptops, printers, scanners, digital cameras, servers, and last but not least, calculators.

Show more

Related categories