The GPU runs at a base clock of 2,295 MHz, reaching a boost of 2,565 MHz under load, while memory operates at 1,438 MHz. With 10,240 shading units and 320 texture mapping units, the card achieves a texture rate of 820.8 GTexels/s and a pixel rate of 287.3 GPixel/s, supported by 112 render output units. Floating-point throughput stands at 52.53 TFLOPS, and Double Precision Floating Point (DPFP) is supported, making the card applicable to compute workloads that extend beyond conventional graphics rendering.
The card features 16GB of GDDR6X VRAM running at an effective speed of 23,000 MHz across a 256-bit bus, delivering a peak memory bandwidth of 736.3 GB/s. ECC memory support is also present, providing data integrity assurance for compute workloads where memory error correction is a relevant consideration.
The card supports DirectX 12 Ultimate, OpenGL 4.6, and OpenCL 3, covering the main graphics and compute API requirements. Ray tracing and DLSS are both enabled alongside stereoscopic 3D, and multi-display technology allows up to four screens to be driven simultaneously. RGB lighting is present, and Intel Resizable BAR is supported to broaden CPU access to GPU memory. XeSS (XMX) and LHR are not available on this model.
Display output is provided through three DisplayPort outputs and one HDMI 2.1a port, totaling four available connections. USB-C, DVI, and mini DisplayPort are not present on this card.
Grounded in the Ada Lovelace architecture and produced on a 5 nm process, the GPU packs 45,900 million transistors and connects to the host platform via PCIe 4. Its 320W TDP is managed through air cooling alone, as water-cooling support is not available. The card measures 306.8 mm in width and 119.4 mm in height.