NVIDIA RTX PRO 2000 16GB Blackwell Low Profile

1,639 €

NVIDIA RTX PRO 2000 16GB Blackwell Low Profile

NVIDIA logo

NVIDIA RTX PRO 2000 16GB Blackwell Low Profile graphics card

The NVIDIA RTX PRO 2000 16GB Blackwell Low Profile delivers 5th-generation Tensor Cores with FP4 support, 4th-generation RT Cores with RTX Mega Geometry, and 16GB of GDDR7 ECC memory in a dual-slot, half-height design that is 167mm long with a TBP of 70W and no external power. With 545 AI TOPS of performance – more than five times that of the previous Ada Lovelace generation at the same power consumption – and ISV certifications for key professional applications, the NVIDIA RTX PRO 2000 16GB Blackwell is a generation ahead without demanding more space or power supply capacity.

Nvidia GeForce RTX 40

GDDR7 / 16GB

Operating memory
NVIDIA GPU

PCIe 5.0 x8

Bus interface
NVIDIA GPU

None

Additional power supply
Nvidia GeForce RTX 40

Blackwell (GB206)

Chip architecture
Nvidia GeForce RTX 40

550W

Recommended PSU wattage
NVIDIA RTX PRO 2000 graphics card

Key features of the NVIDIA RTX PRO 2000 16GB Blackwell Low Profile graphics card

  • The card has 16GB of GDDR7 ECC memory with 288GB/s bandwidth on a 128-bit bus for smooth work with CAD assemblies, 3D visualisations, generative AI, and local AI inference without memory compromises in a compact professional environment
  • The NVIDIA Blackwell architecture with 4352 CUDA cores, 5th-generation Tensor Cores, and a boost frequency of up to 1950MHz achieves 545 AI TOPS and 17 TFLOPS in FP32 – a significant leap over the previous generation at an identical TBP of 70W
  • 4th-generation RT Cores with 52 TFLOPS performance and RTX Mega Geometry technology can process up to 100× more ray-traced triangles than the previous generation for photorealistic visualisations and real-time engineering rendering
  • 5th-generation Tensor Cores with FP4 support and DLSS 4 Multi Frame Generation accelerate generative AI, local LLM inference, and AI-assisted creative tools directly on a compact workstation without reliance on the cloud
  • New Streaming Multiprocessors with neural shaders integrate neural networks directly into programmable shaders for next-generation AI-augmented graphics workflows, even in the most compact professional design
  • The card requires no external power connector – it draws 70W directly from the PCIe 5.0 slot, making installation instant and keeping PSU and cable management demands to a minimum
  • Four mini DisplayPort 2.1b outputs let you connect four monitors simultaneously at 4K resolution at 165Hz or two displays at 8K at 100Hz with HDR and extended colour depth
  • The 9th-generation NVENC video encoder and 6th-generation NVDEC decoder with support for 4:2:2 10-bit H.264 and HEVC provide hardware acceleration for video processing and streaming for creative and production workflows

545 AI TOPS for local agentic AI with data protection

Generations change, but the dimensions of compact workstations remain. That's why the NVIDIA RTX PRO 2000 16GB Blackwell Low Profile delivers the most important thing: a dramatic increase in AI performance without needing to change a thing about your infrastructure. The 5th-generation Tensor Cores with FP4 support achieve 545 AI TOPS – more than five times that of the previous Ada Lovelace generation – at an identical 70W TBP and in a half-height format. For designers working with generative AI, architects using AI-assisted modelling, or developers testing local models on a compact workstation, the RTX PRO 2000 Blackwell is the natural starting point for the new generation.

NVIDIA GPU

16GB GDDR7 and RTX Mega Geometry for mainstream professionals

With 16GB of GDDR7 ECC memory and 288GB/s bandwidth, the NVIDIA RTX PRO 2000 16GB Blackwell Low Profile brings a capacity that was previously not a given in this segment. The card handles CAD assemblies with thousands of components, complex 3D scenes, and generative AI models without overflowing into system RAM, while ECC protection eliminates computational errors for reliable production results. The 4th-generation RT Cores with RTX Mega Geometry then add photorealistic ray tracing with the ability to process up to 100× more ray-traced triangles than the previous generation – even in the most compact professional GPU ever.

NVIDIA GPU

Blackwell generation performance without the need for powerful PSUs

Industrial control stations, on-location media production, and financial analysis terminals have a common denominator: performance must come in a small package. The NVIDIA RTX PRO 2000 16GB Blackwell Low Profile, with its 2.7" × 6.6" dimensions and 70W TBP without external power, opens up access to the Blackwell architecture for all these scenarios. PCIe 5.0 with double the throughput of Gen 4, ISV certifications for key professional applications, and NVIDIA enterprise drivers guarantee proven stability and readiness for production deployment – regardless of system size or installation location.

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

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

16GB GDDR7 ECC

288GB/s for uncompromising CAD, 3D visualisation and local AI inference
Nvidia GeForce RTX 40

New streaming multiprocessors

Neural shaders for a new generation of 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 monitors at 4K@165Hz or two at 8K@100Hz
Nvidia GeForce RTX 40

Half-height 167mm

Deployment wherever standard cards physically won't fit
Nvidia GeForce RTX 40

PCIe 5.0 x8

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

Specifications

Chip

Chip manufacturer NVIDIA
Model designation RTX PRO 2000
Graphics processor GB206
Chip architecture Blackwell
Number of stream processors 4,352×
Production technology 4 nm

Performance & usage

Use Professional
Card profile Low Profile (LP)

Memory

VRAM capacity 16 GB
Memory type GDDR7
Bus width 128-Bit

Frequency

Core frequency 790 MHz
Core clock speed (Boost clock) 1,950 MHz
Memory frequency 18,000 MHz (18 GHz)
Effective memory clock (bandwidth) 18 Gbps

Interface

PC connection PCI Express x16 5.0
Bus interface PCIe 5.0 x8
Monitor connection mini DisplayPort 2.1

Technology

DirectX version 12 Ultimate

Cooling system

Cooling type Active
Cooling size Dual-slot
number of fans 1 ×

Dimensions

Width 167.64 mm
Depth 68.58 mm

Consumption

TDP 70 W

AI

Total number of TOPS 545
Supported precision FP64, FP32, BF16, FP16, FP8, INT8

Tops

Total number of TOPS 545

AI specifications

Primary AI use Workstation AI
CUDA version 12.x
Code:  NVrpr08
Warranty: 36 months
Links: Producer's Website: