Higher GPU clock speeds and double the memory. These are the parameters that characterize the Radeon RX 7600 XT compared to the non-XT model (RX 7600). At the same time, it is a very affordable solution attractive for users prioritizing large video memory, even with a relatively weaker GPU (it doesn’t matter that much…). In our tests, we’ll break down how Sapphire’s design – the RX 7600 XT Pulse – fares in games and beyond.
| Parameters | Sapphire RX 7600 XT Pulse | |
| MSI RTX 4070 Ti Suprim X 12G | ||
| Architecture | RDNA 3 | |
| Die | Navi 33 XT (215-163000047) | |
| Manufacturing node | 6 nm TSMC | |
| Die size | 204 mm² | |
| Transistor count | 13,3 bn. | |
| Compute units | 32 | |
| Shaders/CUDA cores | 2048 | |
| Base Clock | 1980 MHz | |
| Game Clock (AMD) | 2539 MHz | |
| Boost Clock | 2810 MHz | |
| RT units | 32 | |
| AI/tensor cores | – | |
| ROPs | 64 | |
| TMUs | 128 | |
| L2 Cache | 2 MB | |
| Infinity Cache | 32 MB | |
| Interface | PCIe 4.0 ×8 | |
| Multi-GPU interconnect | – | |
| Memory | 16 GB GDDR6 | |
| Memory clock (effective) | 18.0 GHz | |
| Memory bus | 128 bit | |
| Memory bandwidth | 288.0 GB/s | |
| Pixel fillrate | 176.3 Gpx/s | |
| Texture fillrate | 352.6 Gtx/s | |
| FLOPS (FP32) | 22.57 TFLOPS | |
| FLOPS (FP64) | 680 GFLOPS | |
| FLOPS (FP16) | 44.14 TFLOPS | |
| AI/tensor TOPS (INT8) | – | |
| AI/tensor FLOPS (FP16) | – | |
| TDP | 192 W | |
| Power connectors | 2× 8-pin | |
| Card lenght | 250 mm | |
| Card slots used | 45 mm | |
| Shader Model | 6.7 | |
| DirectX/Feature Level | Dx 12 | |
| OpenGL | 4.6 | |
| Vulkan | 1.3 | |
| OpenCL | 2.2 | |
| CUDA | – | |
| Video encoder engine | VCN 4.0 | |
| Encoding formats | HEVC (10 bit), H.264, AV1 (10 bit) | |
| 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 (165 Hz) | |
| HDMI | 2× (2.1a) | |
| DisplayPort | 2× (2.1 UHBR 10) | |
| USB-C | – | |
| MSRP | 329 EUR |
