Equipped with the NVIDIA GB10 Grace Blackwell Superchip, the Dell Pro Max AI Workstation delivers petaflop-scale performance for local AI training, inference, and workload deployments while occupying a deceptively small footprint. The Pro Max can provide up to 1 petaFLOP (1000 TFLOPS) of FP4 compute power.
Featuring a combined Cortex-X925 10-Core and Cortex-A725 10-Core processor, 128GB of unified LPDDR5x memory, and a 2TB M.2 NVMe PCIe 4.0 SSD, the Pro Max is ready to handle a wide range of workloads with the NVIDIA AI software stack, including prototyping, fine-tuning and inference, and data science applications. Three USB 3.2 Gen 2x2 ports are available and a USB-C port serves as a power input for the included 280W adapter while the other three work with up to 20 Gb/s compatible peripherals. There is also an HDMI 2.1b port for external displays. Wi-Fi 7 (802.11be) support and a 10 Gb/s RJ45 Ethernet port provide high-speed connections to compatible networks. Two 200 Gb/s QSFP112 ports on the NVIDIA ConnectX-7 SmartNIC adapter allow you to scale performance by linking multiple Dell Pro Max systems (sold separately) together to handle large models. The NVIDIA DGX OS operating system is preinstalled.