NVIDIA has rolled out two new professional graphics cards at SIGGRAPH 2025. These cards broaden its Blackwell architecture range, introducing the RTX PRO 4000 SFF Edition and RTX PRO 2000. These compact GPUs aim to speed up AI for professional tasks while staying energy-efficient. The graphics cards come with fourth-generation RT Cores and fifth-generation Tensor Cores. They pack major performance boosts into smaller sizes. The RTX PRO 4000 SFF Edition boasts 24 GB of ECC GDDR7 memory. It churns out 770 AI TOPS of throughput. This means it can handle AI tasks up to 2.5 times faster and ray tracing 1.7 times better than older models (i.e. RTX A4000). While bringing updated specs, NVIDIA managed to keep the same 70 W TGP as the card it replaces.

The RTX PRO 2000 comes with 16 GB of ECC GDDR7 memory and targets mainstream design and AI workflows with its 545 AI TOPS of power. Compared with the NVIDIA RTX A2000, it makes 3D modeling up to 1.6 times faster, improves CAD performance by 1.4 times, and speeds up rendering. Performance improvements can also be seen in AI with image generation being 1.4 times quicker and text generation 2.3 times faster. Both GPUs are particularly suited for compact workstations with limited space or tight power budgets. The RTX PRO 2000 will be available through PNY and TD SYNNEX, while both cards will be offered in complete systems from manufacturers including Dell, HP, and Lenovo. These graphics cards are expected to launch later this year, though specific pricing has not been disclosed.