Brand: NVIDIA | Category: GPUs
SKU: NVID-9005G1402200000 | Part #: 900-5G140-2200-000 | MPN: 900-5G140-2200-000
Contact for Pricing — Request a Quote
The NVIDIA RTX PRO 2000 Blackwell is a professional discrete GPU built on NVIDIA's fifth-generation Blackwell GPU architecture, designed specifically to bring enterprise-class compute, visualization, and AI inference capabilities into small-form-factor (SFF) and mainstream professional desktop systems. Featuring 16GB of dedicated GDDR7 memory with ECC support, the card provides the memory headroom required for complex 3D scenes, simulation datasets, and generative AI model inference without demanding the chassis space or power infrastructure of full-height, dual-slot workstation GPUs. Its low-profile, single-slot-compatible design makes it uniquely suited for compact professional desktops where thermal and mechanical constraints have historically limited GPU performance.
| Manufacturer | NVIDIA |
| Product Line | RTX PRO |
| GPU Architecture | Blackwell (5th Generation) |
| GPU Memory | 16 GB GDDR7 |
| Memory Interface Width | 128-bit |
| Memory Bandwidth | Up to 448 GB/s |
| ECC Memory Support | Yes (Error Correcting Code) |
| CUDA Cores | ~3072 (Blackwell CUDA cores) |
| Tensor Core Generation | 5th Generation (FP8/FP16/BF16/TF32) |
| RT Core Generation | 4th Generation |
| NVENC / NVDEC Engines | Dual NVENC / Dual NVDEC (AV1, H.265, H.264) |
| Display Outputs | 4x DisplayPort 2.1 |
| Maximum Display Resolution | 7680 x 4320 (8K) at 60Hz |
| Maximum Simultaneous Displays | 4 |
| Form Factor | Low-Profile, Single-Slot |
| Chassis Compatibility | SFF and Mainstream Professional Desktops; Low-Profile PCIe slots |
| PCIe Interface | PCIe 5.0 x16 |
| Thermal Design Power (TDP) | 70W (approx.) |
| Power Connector | No additional power connector required (slot-powered) |
| API Support | DirectX 12 Ultimate, Vulkan 1.3, OpenGL 4.6, OpenCL 3.0, CUDA 12.x |
| NVIDIA Software Ecosystem | RTX Enterprise drivers, CUDA 12.x, TensorRT, DLSS 4, NVIDIA AI Workbench compatible |
| Virtualization Support | NVIDIA vPC / vWS / vCS (with appropriate licensing) |
| Launch Generation | 2025 Q3 |
Available from Omnixon Global. Submit an RFQ and our team will confirm configuration and availability for your order.
| Brand | NVIDIA |
| Category | GPUs |
| SKU | NVID-9005G1402200000 |
| Part Number | 900-5G140-2200-000 |
| Condition | New |
| Product Line | RTX PRO |
| GPU Architecture | Blackwell (5th Generation) |
| GPU Memory | 16 GB GDDR7 |
| Memory Interface Width | 128-bit |
| Memory Bandwidth | Up to 448 GB/s |
| ECC Memory Support | Yes (Error Correcting Code) |
| CUDA Cores | ~3072 (Blackwell CUDA cores) |
| Tensor Core Generation | 5th Generation (FP8/FP16/BF16/TF32) |
| RT Core Generation | 4th Generation |
| NVENC / NVDEC Engines | Dual NVENC / Dual NVDEC (AV1, H.265, H.264) |
| Display Outputs | 4x DisplayPort 2.1 |
| Maximum Display Resolution | 7680 x 4320 (8K) at 60Hz |
| Maximum Simultaneous Displays | 4 |
| Form Factor | Low-Profile, Single-Slot |
| Chassis Compatibility | SFF and Mainstream Professional Desktops; Low-Profile PCIe slots |
| PCIe Interface | PCIe 5.0 x16 |
| Thermal Design Power (TDP) | 70W (approx.) |
| Power Connector | No additional power connector required (slot-powered) |
| API Support | DirectX 12 Ultimate, Vulkan 1.3, OpenGL 4.6, OpenCL 3.0, CUDA 12.x |
| NVIDIA Software Ecosystem | RTX Enterprise drivers, CUDA 12.x, TensorRT, DLSS 4, NVIDIA AI Workbench compatible |
| Virtualization Support | NVIDIA vPC / vWS / vCS (with appropriate licensing) |
| Launch Generation | 2025 Q3 |
The NVIDIA RTX PRO 2000 Blackwell accelerates AI/ML training, inference, scientific HPC, and virtualization (vGPU) workloads. Typical deployments include LLM training clusters, computer-vision pipelines, financial risk modeling, and rendering farms.
The NVIDIA RTX PRO 2000 Blackwell accelerates AI/ML training, inference, scientific HPC, and virtualization (vGPU) workloads. Typical deployments include LLM training clusters, computer-vision pipelines, financial risk modeling, and rendering farms.
The NVIDIA RTX PRO 2000 Blackwell accelerates AI/ML training, inference, scientific HPC, and virtualization (vGPU) workloads. Typical deployments include LLM training clusters, computer-vision pipelines, financial risk modeling, and rendering farms.
Key specifications for the NVIDIA RTX PRO 2000 Blackwell: new condition; manufacturer NVIDIA; product line RTX PRO; gpu architecture Blackwell (5th Generation); gpu memory 16 GB GDDR7; memory interface width 128-bit; memory bandwidth Up to 448 GB/s. Manufacturer part number 900-5G140-2200-000. For the full datasheet with electrical, environmental, and compliance details, contact our pre-sales engineering team.
Key specifications for the NVIDIA RTX PRO 2000 Blackwell: new condition; manufacturer NVIDIA; product line RTX PRO; gpu architecture Blackwell (5th Generation); gpu memory 16 GB GDDR7; memory interface width 128-bit; memory bandwidth Up to 448 GB/s. Manufacturer part number 900-5G140-2200-000. For the full datasheet with electrical, environmental, and compliance details, contact our pre-sales engineering team.