900-5G153-2570-000 - NVIDIA RTX PRO 5000 Blackwell GPU, 72GB GDDR7, Retail - Refurb'd

Nvidia

SKU: 900-5G153-2570-000

Please Call for Price & Availability.

Manufacturer: Nvidia
Manufacturer Ordering Part #: 900-5G153-2570-000
Condition: REFURBISHED
Availability: Contact / Request A Quote For Current Availability

NVIDIA RTX PRO 5000 Blackwell GPU - Retail Boxed Version - 72 GB GDDR7 with error-correction code (ECC) - Display Ports: 4x DisplayPort 2.1b - Max Power Consumption: 300 W - Graphics Bus: PCIe 5.0 x16 - Form Factor: 4.4” x 10.5” L, dual slot, full height - Thermal: Active

Unlock next-level AI performance and neural rendering capabilities with NVIDIA RTX PRO 5000 Blackwell GPUs. Built on the NVIDIA Blackwell architecture and equipped with 72 GB of ultra-fast GDDR7 memory, it accelerates everything from AI development, large language model (LLM) inference, and agentic AI workflows, along with high-fidelity simulations, video production, and complex 3D modeling from your desktop. With twice the memory of the last generation, you can work with big data, make complex 3D models, and run AI-enhanced multi-app workflows without interruption.

GPU Architecture: NVIDIA Blackwell

NVIDIA CUDA Cores: 14,080

Tensor Cores: Fifth generation

Ray Tracing Cores: Fourth generation

AI TOPS: 2,064 AI TOPS

Single-Precision Performance: 65 TFLOPS

RT Core Performance: 196 TFLOPS

GPU Memory: 72 GB GDDR7 with ECC

Memory Interface: 384-bit

Memory Bandwidth: 1,344 GB/s

System Interface: PCIe 5.0 x16

Display Connectors: 4x DisplayPort 2.1b

Max Simultaneous Displays: 4x 4,096 x 2,160 @ 120 Hz | 4x 5,120 x 2,880 @ 60 Hz | 2x 7,680 x 4,320 @ 60 Hz

Video Engines: 3x NVENC (ninth generation) | 3x NVDEC (sixth generation)

MIG Support: Up to 2x 36 GB | Up to 1x 72 GB

Power Consumption: Total board power - 300 W

Power Connector: 1x PCIe CEM5 16-pin

Thermal Solution: Active

Form Factor: 4.4” x 10.5” L, dual slot, full height

Graphics APIs: DirectX 12, Shader Model 6.6, OpenGL 4.6, Vulkan 1.4

Compute APIs: CUDA 12.8, OpenCL 3.0, DirectCompute