NVIDIA Launches Compact Blackwell Workstation GPUs for AI & Design
NVIDIA has recently introduced two new compact GPUs, the NVIDIA RTX PRO 4000 Blackwell SFF Edition and the NVIDIA RTX PRO 2000 Blackwell, designed to bring next-generation performance to a wide array of professional workflows. These new cards integrate NVIDIA’s fourth-generation RT Cores for advanced ray tracing and fifth-generation Tensor Cores for AI acceleration, delivering significant performance enhancements while consuming less power and occupying roughly half the physical space of traditional GPUs. This compact design makes them ideal for small form factor workstations, enabling powerful capabilities in engineering, design, content creation, AI development, and 3D visualization.
The RTX PRO 4000 SFF Edition represents a substantial leap over its previous-generation architecture. It boasts up to 2.5 times higher AI performance, a 1.7 times increase in ray-tracing capabilities, and 1.5 times more bandwidth, all while maintaining the same efficient 70-watt maximum power consumption. This makes it particularly well-suited for demanding tasks that benefit from accelerated AI and realistic rendering, allowing professionals to achieve greater efficiency without compromising on power.
Targeting mainstream design and AI workflows, the RTX PRO 2000 also delivers notable improvements. Compared to its predecessor, it offers up to 1.6 times faster 3D modeling, a 1.4 times boost in computer-aided design (CAD) performance, and 1.6 times quicker rendering speeds. Furthermore, the RTX PRO 2000 significantly enhances generative AI applications, providing a 1.4 times boost in image generation and a remarkable 2.3 times acceleration in text generation. These enhancements are crucial for professionals seeking faster iteration cycles, rapid prototyping, and seamless collaboration in creative and technical fields.
These new GPUs are not standalone; they integrate deeply with NVIDIA’s extensive software ecosystem, which is designed to harness the full power of AI and advanced graphics for creators, developers, and enterprises. The NVIDIA AI Enterprise software suite provides robust, enterprise-grade tools for building, deploying, and scaling production AI solutions, spanning generative AI, computer vision, speech, and natural language processing across various infrastructures. Complementing this, the NVIDIA Cosmos platform offers world foundation models optimized for fast, efficient inference and edge deployment, enabling high-performance AI for robotics, automation, and physical AI applications. Notably, the Cosmos-Reason1-7B model can run seamlessly on the RTX PRO 4000 SFF, extending powerful physical AI reasoning capabilities to edge devices, compact workstations, and industrial systems.
NVIDIA’s graphics and visualization tools, including the NVIDIA Omniverse platform, further integrate generative physical AI and simulation into 3D design pipelines, facilitating the creation of digital twins and advanced visual workflows. The broader Blackwell platform also leverages NVIDIA’s rich ecosystem of powerful development tools, including the NVIDIA CUDA-X libraries, and is supported by a vast community of over 6 million developers and close to 6,000 applications, ensuring scalable performance across a multitude of GPUs.
Both the NVIDIA RTX PRO 2000 Blackwell and NVIDIA RTX PRO 4000 Blackwell SFF Edition GPUs are expected to become available later this year. The RTX PRO 2000 will be distributed through partners like PNY and TD SYNNEX, as well as system builders such as BOXX, Dell Technologies, HP, and Lenovo. Similarly, the RTX PRO 4000 Blackwell SFF Edition will be available from global distribution partners and leading manufacturing partners including Dell Technologies, HP, and Lenovo, making these powerful compact solutions accessible to a wide professional audience.