The most “lightweight” AMD Navi 31 (XL) GPU, the slowest memory subsystem, but also the lowest price. That’s the RX 7900 GRE compared to the RX 7900 XT. This Radeon is also noticeably cheaper compared to the RTX 4070 Super, although the GeForce’s power efficiency is more favourable. The gaming performance of the RX 7900 GRE (RTX 4070S), meanwhile, is comparable. That is, as long as you won’t miss ray-tracing graphics..
| Parameters | Sapphire RX 7900 XT Pulse | |
| Architecture | RDNA 3 | |
| Die | Navi 31 XL (215-145000206) | |
| Manufacturing node | 5 nm + 6 nm | |
| Die size | 300 mm² + 4× 37 mm² | |
| Transistor count | <58 bn. | |
| Compute units | 80 | |
| Shaders/CUDA cores | 5120 | |
| Base Clock | 1681 MHz | |
| Game Clock (AMD) | 2052 MHz | |
| Boost Clock | 2450 MHz | |
| RT units | 80 | |
| AI/tensor cores | – | |
| ROPs | 160 | |
| TMUs | 320 | |
| L2 Cache | 6 MB | |
| Infinity Cache | 64 MB | |
| Interface | PCIe 4.0 ×16 | |
| Multi-GPU interconnect | – | |
| Memory | 16 GB GDDR6 | |
| Memory clock (effective) | 18.0 GHz | |
| Memory bus | 256 bit | |
| Memory bandwidth | 576.0 GB/s | |
| Pixel fillrate | 382.6 Gpx/s | |
| Texture fillrate | 765.1 Gtx/s | |
| FLOPS (FP32) | 49.0 TFLOPS | |
| FLOPS (FP64) | 1530.0 GFLOPS | |
| FLOPS (FP16) | 97.94 TFLOPS | |
| AI/tensor TOPS (INT8) | – | |
| AI/tensor FLOPS (FP16) | – | |
| TDP | 260 W | |
| Power connectors | 2× 8-pin | |
| Card lenght | 302 mm | |
| Card slots used | 56 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 (10 bit), H.264,VP9 (10 bit), AV1 (10 bit) | |
| Decoding resolution | 8K | |
| Max. Monitor resolution | 7680 × 4320 px | |
| HDMI | 2× (2.1a) | |
| DisplayPort | 2× (2.1 UHBR) | |
| USB-C | – | |
| MSRP | 615 EUR |
