PNY NVIDIA RTX PRO 4000 Blackwell 24GB GDDR7 ECC

3,329 €

PNY NVIDIA RTX PRO 4000 Blackwell 24GB GDDR7 ECC

PNY

PNY NVIDIA RTX PRO 4000 Blackwell 24GB GDDR7 ECC graphics card

PNY NVIDIA RTX PRO 4000 Blackwell 24GB delivers the full power of the GB203 chip – 8960 CUDA cores, 5th generation Tensor cores with FP4 support and 24GB of GDDR7 ECC memory – in a single-slot, 241mm FHML design with blower cooling. With a TBP of 140W, Frame Lock support via NVIDIA RTX PRO Sync and a hardware JPEG encoder, the PNY NVIDIA RTX PRO 4000 Blackwell 24GB goes beyond a standard workstation GPU and targets environments where multi-GPU synchronisation, visualisation studios and production deployments place different demands on hardware than performance alone.

Nvidia GeForce RTX 40

GDDR7 / 24GB

Operating memory
NVIDIA GPU

PCIe 5.0 x16

Bus interface
NVIDIA GPU

Not present

Additional power
Nvidia GeForce RTX 40

Blackwell (GB203)

Chip architecture
Nvidia GeForce RTX 40

550W

Recommended source power
NVIDIA GPU

Key features of the PNY NVIDIA RTX PRO 4000 Blackwell 24GB GDDR7 ECC graphics card

  • The card has 24GB of GDDR7 ECC memory on a 192-bit bus for smooth work with large AI models, complex CAD assemblies and demanding rendering scenes, with ECC protection for flawless results in production deployments
  • The NVIDIA GB203 chip with 8960 CUDA cores, 280 5th generation Tensor cores and 70 4th generation RT cores on a TSMC 4N process with 45.6 billion transistors on a 378mm² area forms a powerful foundation for AI inference, generative AI and professional visualisation
  • 5th generation Tensor cores with FP4 support and DLSS 4 Multi Frame Generation deliver up to 3× more performance than the previous generation for local LLM fine-tuning, generative AI workflows and AI-assisted creative applications
  • 4th generation RT cores with RTX Mega Geometry technology enable the processing of up to 100× more ray-traced triangles than the previous generation for physically accurate visualisations, engineering simulations and real-time VFX production
  • The single-slot, 241mm FHML design with blower cooling saves the adjacent slot in the build and, with active heat exhaust directly out of the case, ensures reliable cooling even in multi-card workstation configurations
  • Frame Lock support via NVIDIA RTX PRO Sync enables hardware synchronisation of multiple GPU outputs for visualisation installations, multi-projection environments and professional broadcasting workflows that require perfect frame timing
  • The card is powered by a 1× PCIe CEM5 16-pin connector with a TBP of 140W; the recommended power supply for a workstation setup is at least 650W
  • Two 9th generation NVENC video encoders, two 6th generation NVDEC decoders and a dedicated JPEG encoder provide hardware acceleration for professional video, streaming and real-time image data processing

Single-slot GB203 for multi-GPU configurations

In multi-GPU workstations, every slot counts – and the single-slot design of the PNY NVIDIA RTX PRO 4000 Blackwell 24GB lets you install more cards where a dual-slot design would hit space limits. The blower cooler with active heat exhaust prevents heat from accumulating near adjacent components, even under continuous production loads. With a TBP of 140W and a PCIe 5.0 x16 interface, the card delivers the full performance of the GB203 chip with 45.6 billion transistors without spatial compromises – the ideal foundation for visualisation studios, simulation environments and multi-card AI configurations where performance density per slot matters.

NVIDIA GPU

Frame Lock and JPEG encoder

Computational power is only half of the equation – the other half is how quickly data gets to and from the GPU. The PNY NVIDIA RTX PRO 4000 Blackwell 24GB combines a PCIe 5.0 x16 interface with double the throughput of Gen 4 and 24GB of GDDR7 ECC memory to eliminate data bottlenecks when working with large AI datasets, 3D scenes or multi-application workflows. New neural shaders in the Blackwell architecture integrate AI directly into the graphics pipeline, while ISV certifications and NVIDIA enterprise drivers guarantee proven stability for production deployments – from design studios and engineering labs to financial analysis centres.

NVIDIA GPU

Data throughput for AI and 3D without bottlenecks

Computational power is only half of the equation – the other half is how quickly data gets to and from the GPU. The PNY NVIDIA RTX PRO 4000 Blackwell 24GB combines a PCIe 5.0 x16 interface with double the throughput of Gen 4 and 24GB of GDDR7 ECC memory to eliminate data bottlenecks when working with large AI datasets, 3D scenes or multi-application workflows. New neural shaders in the Blackwell architecture integrate AI directly into the graphics pipeline, while ISV certifications and NVIDIA enterprise drivers guarantee proven stability for production deployments – from design studios and engineering labs to financial analysis centres.

NVIDIA GPU
Nvidia GeForce RTX 40

NVIDIA Blackwell architecture

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

5th generation Tensor cores

1178 AI TOPS with FP4 for local AI inference and generative AI applications
Nvidia GeForce RTX 40

24GB GDDR7 ECC

432GB/s for large-scale AI models and complex 3D scenes in an SFF format
Nvidia GeForce RTX 40

New Streaming Multiprocessors

Neural shaders for next-generation AI-augmented graphics workflows
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 four 4K@165Hz monitors or two 8K@100Hz monitors
Nvidia GeForce RTX 40

Single-slot FHML design

Blower cooling and 241mm length for multi-card workstation configurations
Nvidia GeForce RTX 40

PCIe 5.0 x16

Double the throughput of PCIe Gen 4 for data-intensive AI tasks

Specifications

Chip

Chip manufacturer NVIDIA
Model designation RTX PRO 4000
Graphics processor GB203
Chip architecture Blackwell
Number of stream processors 8,960×
Production technology 4 nm

Performance & usage

Use Professional
Card profile FHFL

Memory

VRAM capacity 24 GB
Memory type GDDR7
Bus width 192-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

DirectX version 12 Ultimate

Cooling system

Cooling type Active
Cooling size One-slotted
number of fans 1 ×

Dimensions

Width 241 mm
Depth 111 mm

Consumption

TDP 140 W

AI

Total number of TOPS 1,178
Supported precision FP64, FP32, BF16, FP16, FP8, INT8

Tops

Total number of TOPS 1,178

AI specifications

Primary AI use Workstation AI
CUDA version 11.x
Code:  PNYrpb02
Warranty: 36 months
Links: Producer's Website:
Manufacturer information

PNY Technologies Europe, ZAC du Phare 9 rue Joseph Cugnot 33708 Mérignac cedex, France https://www.pny.com/en-eu/support-footer/technical-support

Show more