The card runs at a base clock of 2280 MHz, climbing to a boost frequency of 2580 MHz under load, and its 3,840 shading units are paired with 120 texture mapping units and 48 render output units to support a texture rate of 309.6 GTexels/s and a pixel rate of 123.8 GPixel/s. Overall floating-point throughput reaches 19.81 TFLOPS, while the GPU memory operates at 1750 MHz. Double Precision Floating Point (DPFP) is supported, rounding out a performance profile suited to a range of compute and graphics workloads.
The card is equipped with 8GB of GDDR7 VRAM running across a 128-bit memory bus at an effective speed of 28,000 MHz, yielding a maximum memory bandwidth of 448 GB/s. ECC memory support is included, adding a layer of data integrity for workloads where memory accuracy is a consideration.
On the software and API side, the card supports DirectX 12 Ultimate, OpenGL 4.6, and OpenCL 3, covering a broad range of graphics and compute applications. Ray tracing and DLSS are both supported, while XeSS (XMX) is not available. Multi-display technology is included, with support for up to four simultaneous displays, and stereoscopic 3D is also supported. Intel Resizable BAR is present to help improve data transfer between the CPU and GPU, and there is no LHR limitation. RGB lighting is built into the card's design.
The card's output configuration consists of one HDMI 2.1b port and three DisplayPort outputs, totaling four display connections. There are no USB-C, DVI, or mini DisplayPort outputs on this model.
Built on the Blackwell architecture, this card uses a 5 nm manufacturing process and integrates 21,900 million transistors, with a TDP of 145W and a PCIe 5.0 interface for system connectivity. It measures 300.5 mm in width and 120 mm in height, and relies solely on air cooling without any water-cooling support.