PNY NVIDIA RTX PRO 5000 72GB Blackwell GPU
Free Shipping
More finance options:
Estimated Shipping Widget will be displayed here!
Orders placed between Monday - Friday before
1:00 PM PST will most likely ship out the same day. We work hard to process and ship your items quickly so you can start enjoying them as soon as possible.
Found a lower price? Contact us and we'll see if we can match it! Price match will only be applied to products sold and shipped by authorized retailers of the brand.
No restocking fee will be charged when you opt for store credit. Exclusions apply.
Condition: New
Description
PNY NVIDIA RTX PRO 5000 72GB Blackwell GPU
The NVIDIA RTX PRO 5000 72GB Blackwell GPU brings next-level AI acceleration, ray tracing performance, and workstation-class reliability to professional creators, engineers, and researchers. Built on the powerful Blackwell architecture, this GPU is engineered to handle generative AI, large LLM inference, massive simulation workloads, complex 3D design, and real-time rendering at unmatched speed.
With 72GB of ultra-fast GDDR7 ECC memory and 1.3 TB per second of memory bandwidth, the RTX PRO 5000 72GB enables smooth operation with multi-application pipelines, large datasets, and dense 3D scenes. Fifth-generation Tensor Cores support FP4 precision for dramatically accelerated AI workflows, while fourth-generation Ray Tracing Cores double geometric throughput for accurate, photorealistic rendering.
Designed for enterprise reliability, the RTX PRO 5000 includes PCIe Gen 5 connectivity, advanced NVENC and NVDEC engines with 4:2:2 support, MIG partitioning for multiple GPU instances, and four DisplayPort 2.1b outputs for ultra-high-resolution displays. It is the ideal professional GPU for AI development, engineering simulation, VFX, virtual production, and scientific computing.
Key Features
- 72GB GDDR7 ECC memory for massive datasets, simulations, and large AI models
- NVIDIA Blackwell architecture delivering breakthrough AI and graphics performance
- Fifth-generation Tensor Cores supporting FP4 precision for faster generative AI
- Fourth-generation Ray Tracing Cores with doubled geometry throughput
- 1.3 TB per second memory bandwidth for high-performance multi-app workflows
- PCIe Gen 5 interface for maximum CPU-to-GPU throughput
- Four DisplayPort 2.1b outputs supporting up to 16K resolution
- Ninth-gen NVENC and sixth-gen NVDEC engines with 4:2:2 support
- MIG capability allowing secure multi-instance GPU partitioning
- Enterprise-grade reliability with workstation-certified stability
Technical Specifications
- Architecture: NVIDIA Blackwell
- CUDA Cores: 14,080
- Tensor Cores: Fifth generation
- Ray Tracing Cores: Fourth generation
- AI Performance: 2,064 AI TOPS
- Single-Precision Performance: 65 TFLOPS
- RT Core Performance: 196 TFLOPS
- Memory: 72GB GDDR7 with ECC
- Memory Interface: 384-bit
- Memory Bandwidth: 1,344 GB per second
- System Interface: PCIe 5.0 x16
- Display Outputs: 4 x DisplayPort 2.1b
- Max Resolution Support: up to 16K at 60 Hz
- Video Engines: 3 x NVENC, 3 x NVDEC
- MIG Support: Up to 2 x 36GB or 1 x 72GB
- Total Board Power: 300 W
- Power Connector: 1 x PCIe CEM5 16-pin
- Thermal Solution: Active cooling
- Form Factor: Full height, dual slot, 4.4 in x 10.5 in
- Graphics APIs: DirectX 12, Shader Model 6.6, OpenGL 4.6, Vulkan 1.3
- Compute APIs: CUDA 12.8, OpenCL 3.0, DirectCompute
