The card operates at a base GPU clock of 2325 MHz, rising to 2557 MHz under boost conditions, and delivers 31.42 TFLOPS of floating-point performance alongside double precision floating point support. Its 6144 shading units work in tandem with 192 texture mapping units and 80 render output units, producing a texture rate of 490.9 GTexels/s and a pixel rate of 204.6 GPixel/s. GPU memory runs at 1750 MHz, contributing to the overall throughput figures that these render and shading resources depend on.
This card is equipped with 12GB of GDDR7 VRAM running across a 192-bit memory bus, reaching an effective speed of 28000 MHz and a maximum memory bandwidth of 672 GB/s. ECC memory support is also included, which helps maintain data integrity during operation by detecting and correcting memory errors.
The card supports ray tracing and DLSS, alongside stereoscopic 3D and multi-display output across up to four screens simultaneously. On the API side, it is compatible with DirectX 12 Ultimate, OpenGL 4.6, and OpenCL 3, covering a broad range of rendering and compute workloads. Intel Resizable BAR is supported, while XeSS (XMX) and LHR are not present. The card does not include RGB lighting.
The card's output configuration consists of one HDMI 2.1b port and three DisplayPort outputs, providing a total of four video connections. There are no USB-C, DVI, or mini DisplayPort outputs available on this model.
Built on the Blackwell architecture and manufactured using a 5 nm process, the GPU integrates 31,100 million transistors and connects to the host system via PCIe 5.0. It carries a thermal design power of 250W and does not include an air-water cooling solution. Physically, the card measures 304 mm in width and 126 mm in height, which is worth factoring in when planning case compatibility.
