The new RTX PRO 6000 Blackwell

The new RTX PRO 6000 Blackwell

The new RTX Pro series is based on the powerful Blackwell architecture and is aimed at professional users who place the highest demands on graphics, simulation and AI. The GPUs of the RTX 6000 series deliver massive performance with simultaneous energy efficiency.

With features such as hardware-accelerated ray tracing, AI-supported image processing, advanced visualisation and high VRAM capacity, they are ideal for CAD, DCC, scientific simulations or machine learning.

RTX Pro Blackwell series

NVIDIA RTX PRO 6000 Blackwell
NVIDIA RTX PRO 6000 Blackwell
Workstation-Edition
CUDA Cores
24064
Tensor Cores
752 (5. Gen)
NVIDIA RT Cores
188 (4. Gen)
PCIe
PCI Express PCIe 5 x16
VRAM
96 GB GDDR7 with ECC
TDP
600 W
Auf Anfrage
Jetzt anfragen
NVIDIA RTX PRO 6000 Blackwell
NVIDIA RTX PRO 6000 Blackwell
Max-Q Workstation Edition
CUDA Cores
24064
Tensor Cores
752 (5. Gen)
NVIDIA RT Cores
188 (4. Gen)
PCIe
PCI Express PCIe 5 x16
VRAM
96 GB GDDR7 with ECC
TDP
300 W
Auf Anfrage
Jetzt anfragen
NVIDIA RTX PRO 6000 Blackwell
NVIDIA RTX PRO 6000 Blackwell
Server-Edition
CUDA Cores
24064
Tensor Cores
752 (5. Gen)
NVIDIA RT Cores
188 (4. Gen)
PCIe
PCI Express PCIe 5 x16
VRAM
96 GB GDDR7 with ECC
TDP
400-600 W
Auf Anfrage
Jetzt anfragen

Properties Supported by NVIDIA Blackwell architecture

Tensor computing units of the 5th generation

Fifth-generation Tensor Cores offer up to 3x more performance than the previous generation, plus support for FP4 precision and DLSS-4 multi-frame generation technology. Accelerates local LLMs, enables prototyping of new AI models and facilitates improved content and graphics production.

4th generation RT computing units

Fourth-generation RT compute units deliver up to 2x the performance of the previous generation and accelerate rendering for M&E content creation, AECO design and prototyping in manufacturing. Create photorealistic, physically accurate scenes and immersive 3D designs with neural graphics-based technologies such as RTX Mega Geometry, which enables up to 100x more triangles with ray tracing.

CUDA computing units

Blackwell is the most powerful professional RTX GPU ever developed, featuring the latest SM and CUDA® core technology. SM features increased processing throughput and new neural shaders that integrate neural networks into programmable shaders to drive the next generation of AI-powered graphics innovation.

96 GB graphics processor memory

New, improved GDDR7 memory significantly increases bandwidth and capacity, allowing your applications to run faster and work with larger, more complex data sets. With 96 GB of GPU memory, you can complete large 3D and AI projects, explore large VR environments and drive even larger multi-app workflows.

Multi-instance GPU

The Multi-Instance GPU (MIG) provides the ability to create up to four (4) fully isolated instances, increasing the performance and value of the RTX PRO 6000 Server Edition. Each MIG instance has its own memory, cache and high-bandwidth compute units with guaranteed quality of service (QoS), extending the reach of accelerated computing resources to all users.

PCIe of the 5th generation

Support for 5th generation PCI Express provides twice the bandwidth of 4th generation PCIe, improving data transfer speeds from CPU memory and enabling faster performance for data-intensive tasks such as AI, data science and 3D modelling.

RTX PRO 6000 Blackwell comparison

NVIDIA RTX PRO 6000 Blackwell
Workstation Edition
NVIDIA RTX PRO 6000 Blackwell
Max-Q Workstation Edition
NVIDIA RTX PRO 6000 Blackwell
Server Edition*
GPU architectureBlackwell
Tensor cores752 (5th Gen)
RT core188 (4th gen)
CUDA cores24,064
Memory size96 GB GDDR7 w/ ECC
Memory bandwidth1792 GB/s1792 GB/s1600 GB/s
MIGUp to 4x 24GB
Up to 2x 48GB
Up to 1x 96GB
Media acceleration4 NVENC (+AV1, 4:2:2)
4 NVDEC (+AV1, 4:2:2)
CoolingDouble-flow-through
Axial, inside chassis
Active blower
Radial, out of chassis
Passive
Form factor5.4" H x 12.0" L,
XHFL Dual Slot
4.4" H x 10.5" L,
FHFL Dual Slot
4.4" H x 10.5" L,
FHFL Dual Slot
Max. Power consumption600W300W400 - 600W Configurable
Power connectionCEM5 16-pin
PCI-E busPCI Express Gen 5 x16
Monitor connections4x DP2.1b
NVIDIA data sheetNVIDIA data sheetNVIDIA datasheet

* All specifications are preliminary

First step

contact sysGen

Allgemeine Daten
Weitere Informationen

Do you need more? Suitable hardware for the RTX PRO 6000 Blackwell

Storage

Our high-performance storage solutions offer high capacity and speed to efficiently store and retrieve large amounts of data. Perfect for the requirements of big data and machine learning.

AI Training Server

Our AI training servers are designed for maximum computing power and flexibility. They enable efficient training of complex AI models and are ideal for research and development.

Inference Hardware

Our inference hardware offers the necessary computing capacity to execute AI models in real time. Ideal for applications such as autonomous vehicles, image processing and voice control.

FAQ - RTX PRO 6000 Blackwell
Ihre optimale Website-Nutzung

Diese Website verwendet Cookies und bindet externe Medien ein. Mit dem Klick auf „✓ Alles akzeptieren“ entscheiden Sie sich für eine optimale Web-Erfahrung und willigen ein, dass Ihnen externe Inhalte angezeigt werden können. Auf „Einstellungen“ erfahren Sie mehr darüber und können persönliche Präferenzen festlegen. Mehr Informationen finden Sie in unserer Datenschutzerklärung.

Detailinformationen zu Cookies & externer Mediennutzung

Externe Medien sind z.B. Videos oder iFrames von anderen Plattformen, die auf dieser Website eingebunden werden. Bei den Cookies handelt es sich um anonymisierte Informationen über Ihren Besuch dieser Website, die die Nutzung für Sie angenehmer machen.

Damit die Website optimal funktioniert, müssen Sie Ihre aktive Zustimmung für die Verwendung dieser Cookies geben. Sie können hier Ihre persönlichen Einstellungen selbst festlegen.

Noch Fragen? Erfahren Sie mehr über Ihre Rechte als Nutzer in der Datenschutzerklärung und Impressum!

Ihre Cookie Einstellungen wurden gespeichert.