The NVIDIA RTX PRO™ 2000 GPU delivers breakthrough performance in a power-efficient, compact form factor. Unlock accelerated multi-application graphics and AI workloads with next-level neural rendering, 3D performance, and AI capabilities. Equipped with the latest gen Tensor Cores, RT Cores, CUDA Cores, and 16 GB of ultra-fast GDDR7 memory, tackle complex product design, content creation, and engineering workflows while collaborating with desktop AI assistants or running AI inference at the edge. Experience the new standard for mainstream professional performance with enterprise-grade support and major ISV certifications, ensuring reliability for mission-critical projects. Innovate and iterate at unprecedented speeds while future-proofing your desktop with the latest generation of AI-powered small form factor workstations.
Features
Powered by NVIDIA Blackwell Architecture
Max AI performance with FP4 and DLSS 4
Optimized for RTX Neural Shaders
Built for RTX Mega Geometry
Fifth-generation Tensor Cores deliver up to 3X the performance of the previous generation and add support for FP4 precision and DLSS 4 Multi Frame Generation technology. Accelerate local LLMs, prototype new AI models, and drive enhanced content creation and graphics.
Fourth-generation RT Cores deliver up to 2X the performance of the previous generation, accelerating rendering for M&E content creation, AECO design, and manufacturing prototyping. Create photoreal, physically accurate scenes and immersive 3D designs with neural graphics-based technologies, such as RTX Mega Geometry, enabling up to 100X more ray-traced triangles.
NVIDIA Blackwell is the most powerful professional RTX GPU ever created with the latest SM and CUDA core technology. The SM features increased processing throughput, and new neural shaders that integrate neural networks inside of programmable shaders to drive the next decade of AI-augmented graphics innovations.
New and improved GDDR7 memory significantly boosts bandwidth and capacity, empowering your applications to run faster, and work with larger, more complex datasets. With 16GB of GPU memory, tackle large 3D and AI projects, explore immersive VR environments, and drive multi-app workflows.
Ninth-generation NVIDIA NVENC engines significantly accelerate video encoding speed, and improve quality for professional video applications. They add support for 4:2:2 H.264 and HEVC encoding, and improve HEVC and AV1 encoding quality.
Sixth-generation NVIDIA NVDEC engines provide up to double H.264 decoding throughput and offer support for 4:2:2 H.264 and HEVC decode. Professionals can benefit from high-quality video playback, accelerate video data ingestion, and use advanced AI-powered video editing features.
Support for PCI Express Gen 5 provides double the bandwidth of PCIe Gen 4, improving data-transfer speeds from CPU memory and unlocking faster performance for data-intensive tasks like AI, data science, and 3D modeling.
With DisplayPort 2.1, professionals can achieve unparalleled visual clarity and performance, driving high-resolution displays at up to 8K at 240Hz and 16K at 60Hz. Increased bandwidth enables seamless multi-monitor setups, ideal for multitasking and collaboration, while HDR and higher color depth support ensures superior color accuracy for precision work, such as video editing, 3D design, and live broadcasting.
| Architecture | NVIDIA Blackwell Architecture |
| CUDA Parallel Processing Cores | 4,352 |
| NVIDIA Tensor Cores | 136 |
| NVIDIA RT Cores | 34 |
| Single-Precision Performance1 | 17 TFLOPS |
| AI Performance1 | 545 AI TOPS2 |
| RT Core Performance1 | 52 TFLOPS |
| GPU Memory | 16 GB GDDR7 with ECC |
| Memory Interface | 128-bit |
| Memory Bandwidth | 288 GB/s |
| Max Power Consumption | 70W |
| Graphics Bus | PCI Express 5.0 x82 |
| Display Connectors | mDP 2.1b (4) |
| Form Factor | 2.7" (H) x 6.6" (L), HHHL Dual Slot |
| Product Weight | With ATX Bracket: .299 kg With Low Profile Bracket: .288 kg |
| Thermal Solution | Blower Active Fan |
| NVENC | NVDEC | JPEG | 1x | 1x | 1x |
PRELIMINARY SPECIFICATIONS. SUBJECT TO CHANGE.
1 Peak rates are based on GPU boost clock.
2 Theoretical FP4 TOPS using the sparsity feature.
3 Uses full length PCIe interface