Key Differences
Advantages of Radeon RX 9070 XT
Advantages of GeForce RTX 5080
Specifications
Performance
| TGP | 304 W | 360 W |
Storage Details
| Bus | 256-bit | 256-bit |
Ports
| DisplayPort | 2.1a | 2.1b |
Other
| Forza Horizon 5 | 245169145111 | 256183173137 |
| The Witcher 3 | 25923717392 | 27023817290 |
| Counter-Strike 2 | 32722616883 | 32523517789 |
| Far Cry 6 | 201174160101 | 19617715697 |
| Hogwarts Legacy | 15813310761 | 18815412069 |
| CoD: Modern Warfare III | 248240178119 | 243243196136 |
| Ghost of Tsushima | 16013311974 | 16814112880 |
| Cyberpunk 2077 | 18716611757 | 22019213761 |
| Shadow of the Tomb Raider | 279269204109 | 295279211112 |
| 1080p High | 229 | 240 |
| 1080p Ultra | 194 | 205 |
| 1440p Ultra | 152 | 163 |
| 4K Ultra | 90 | 97 |
| Margin of Error | Low | Low |
| Time Spy | 29924 | 32989 |
| Solar Bay | 118881 | 158670 |
| Port Royal | 18600 | 23111 |
| Fire Strike | 66456 | 74973 |
| Wild Life Extreme | 54280 | 69192 |
| Night Raid | 198779 | 202226 |
| Background Blur | 427.4 img/sec | 319.6 img/sec |
| Face Detection | 251 img/sec | 225 img/sec |
| Horizon Detection | 6.77 Gpixels/sec | 13.6 Gpixels/sec |
| Edge Detection | 9.42 Gpixels/sec | 19.5 Gpixels/sec |
| Gaussian Blur | 9.35 Gpixels/sec | 20.4 Gpixels/sec |
| Feature Matching | 1.42 Gpixels/sec | 2.33 Gpixels/sec |
| Stereo Matching | 651.4 Gpixels/sec | 1750 Gpixels/sec |
| Particle Physics | 23630 FPS | 43676.6 FPS |
| API | OpenGL | Vulkan |
| G2D Mark | 1327 | 1416 |
| DirectX 11 | 294 FPS | 327 FPS |
| DirectX 12 | 77 FPS | 145 FPS |
| GPU Compute | 15964 Ops/s | 20278 Ops/s |
| Aztec Ruins Normal Tier | 1794.9 FPS | 1955.9 FPS |
| Car Chase | 1498 FPS | - |
| Manhattan 3.1.1 (1440p) | 1199.3 FPS | - |
| T-Rex | 5080.1 FPS | - |
| Tessellation | 6928.5 FPS | - |
| ALU 2 | 9196.7 FPS | - |
| Driver Overhead 2 | 339.1 FPS | - |
| OS | Windows | Windows |
| Image Classification (SP) | 18001 | 15441 |
| Image Segmentation (HP) | 25174 | 47173 |
| Image Super Resolution (Q) | 45714 | 43223 |
| Face Detection (HP) | 74776 | 92863 |
| Pose Estimation (Q) | 196137 | 202202 |
| Text Classification (SP) | 5163 | 3701 |
| Machine Translation (HP) | 8677 | 7905 |
| Object Detection (SP) | 19602 | 20955 |
| Depth Estimation (Q) | 74879 | 69068 |
| Style Transfer (SP) | 411302 | 349205 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
| Vendor | Amd | Nvidia |
| Build | Discrete | Discrete |
| Released | January 7, 2025 | January 7, 2025 |
| Launch price (MSRP) | $599 | $999 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | High-end |
| Architecture | RDNA 4.0 | Blackwell 2.0 |
| GPU Codename | Navi 48 | GB203-400 |
| Rival Equivalent | GeForce RTX 5070 Ti | - |
| Base Clock | 1660 MHz | 2295 MHz |
| Boost Clock | 2970 MHz | 2617 MHz |
| Shading Units | 4096 | 10752 |
| Texture Mapping Units (TMUs) | 256 | 336 |
| Render Output Units (ROPs) | 128 | 112 |
| Compute Units (Pipelines) | 64 | 84 |
| Tensor Cores | 128 | 336 |
| Ray-tracing Cores | 64 | 84 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 4MB shared | 64MB shared |
| Instructions Per Cycle | 4 IPC | 2 IPC |
| Pixel Fill Rate | 380 GPixel/s | 293 GPixel/s |
| Texture Fill Rate | 760 GTexel/s | 879 GTexel/s |
| Interface | PCIe 5.0 x16 | PCIe 5.0 x16 |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 4 nm | 4 nm |
| Die Size | 356.5 mm² | 378 mm² |
| Transistor Count | 53.9 billion | 45.6 billion |
| Transistor Density | 151.19 MTr/mm² | 120.63 MTr/mm² |
| Memory Type | GDDR6 | GDDR7 |
| Memory Size | 16 GB | 16 GB |
| Memory Clock | 2518 MHz | 1875 MHz |
| Effective Memory Speed | 20100 Mbps | 30000 Mbps |
| ECC | No | No |
| DirectX | 12 | 12.2 |
| Vulkan | 1.3 | 1.4 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.2 | 3.0 |
| CUDA | No | 12.0 |
| Ray Tracing | Yes | Yes |
| DLSS | No | DLSS 4 |