The most powerful Radeon (RX 7900 XTX) is both slower and less efficient compared to the GeForce RTX 4090, but it’s also roughly 700 EUR cheaper. And that’s what gives it an unprecedented price/performance ratio for a high-end graphics card. The latter is more attractive even than the lower-end RX 7900 XT, and that’s also the case with Gigabyte’s top-of-the-range Aorus Elite, which, oddly enough, only comes at a minimal premium.
| Parameters | Aorus RX 7900 XTX Elite 24G | |
| Architecture | RDNA 3 | |
| Die | Navi 31 XT (215-145000156) | |
| Manufacturing node | 5 nm + 6 nm | |
| Die size | 300 mm² + 6× 37 mm² | |
| Transistor count | 58 bn. | |
| Compute units | 96 | |
| Shaders/CUDA cores | 6144 | |
| Base Clock | 1900 MHz | |
| Game Clock (AMD) | 2510 MHz | |
| Boost Clock | 2680 MHz | |
| RT units | 96 | |
| AI/tensor cores | – | |
| ROPs | 192 | |
| TMUs | 384 | |
| L2 Cache | 6 MB | |
| Infinity Cache | 96 MB | |
| Interface | PCIe 4.0 ×16 | |
| Multi-GPU interconnect | – | |
| Memory | 24 GB GDDR6 | |
| Memory clock (effective) | 20.0 GHz | |
| Memory bus | 384 bit | |
| Memory bandwidth | 960.0 GB/s | |
| Pixel fillrate | 514.4 Gpx/s | |
| Texture fillrate | 1028.7 Gtx/s | |
| FLOPS (FP32) | 61.0 TFLOPS | |
| FLOPS (FP64) | 1919.0 GFLOPS | |
| FLOPS (FP16) | 122.0 TFLOPS | |
| AI/tensor TOPS (INT8) | – | |
| AI/tensor FLOPS (FP16) | – | |
| TDP | 355 W | |
| Power connectors | 3× 8-pin | |
| Card lenght | 335 mm | |
| Card slots used | 69 mm | |
| Shader Model | 6.7 | |
| DirectX/Feature Level | DX 12 Ultimate (12_2) | |
| OpenGL | 4.6 | |
| Vulkan | 1.3 | |
| OpenCL | 2.2 | |
| CUDA | – | |
| Video encoder engine | VCN 4.0 | |
| Encoding formats | HEVC, H.264, AV1 | |
| Encoding resolution | 8K | |
| Video decoder engine | VCN 4.0 | |
| Decoding formats | HEVC, H.264,VP9, AV1 | |
| Decoding resolution | 8K | |
| Max. Monitor resolution | 7680 × 4320 px | |
| HDMI | 2× (2.1a) | |
| DisplayPort | 2× (2.1 UHBR) | |
| USB-C | – | |
| MSRP | 1205 EUR |
