Quick/Comparisons
The Radeon RX 7900 XTX takes the lead in gaming performance due to its higher score of 81, outpacing the GeForce RTX 5090 Laptop's 70.5.
Both the GeForce RTX 5090 Laptop and Radeon RX 7900 XTX deliver strong workstation performance, with the Radeon RX 7900 XTX edging out the GeForce RTX 5090 Laptop by 2 points.
The Radeon RX 7900 XTX boasts a 14-point advantage in AI/ML compute, thanks to its RDNA 3.0 architecture and 74 score, outperforming the GeForce RTX 5090 Laptop's 60.
71 | Gaming | 81 |
73 | Workstation | 75 |
60 | AI/ML | 74 |
50 | Energy Efficiency | 43 |
67 | Quick Comparison Final Score | 77 |
| GB203-400 | Graphics Processor | Navi 31 |
| 10496 | Cores | 6144 |
| 328 / 112 | TMUs / ROPs | 384 / 192 |
| 8001.96 | Blender GPU | 4055.35 |
| 154 | Forza Horizon 5 | 174 |
| 198 | The Witcher 3 | 256 |
| 213 | Counter-Strike 2 | 232 |
| 155 | Far Cry 6 | 182 |
| 123 | Hogwarts Legacy | 137 |
| 187 | Call of Duty | 255 |
| 115 | Ghost of Tsushima | 138 |
| 155 | Cyberpunk 2077 | 181 |
| 260 | Tomb Raider | 277 |
| 173 | Average FPS | 204 |
| 202 | 1080p High | 241 |
| 173 | 1080p Ultra | 204 |
| 137 | 1440p Ultra | 159 |
| 80 | 4K Ultra | 94 |
| Low | Margin of Error | Low |
| 226752 | GB6 Compute Score | 224686 |
| 266.5 img/sec | Background Blur | 423.9 img/sec |
| 196.9 img/sec | Face Detection | 270.8 img/sec |
| 10.6 Gpixels/sec | Horizon Detection | 9.23 Gpixels/sec |
| 15.2 Gpixels/sec | Edge Detection | 13.7 Gpixels/sec |
| 14.4 Gpixels/sec | Gaussian Blur | 11.1 Gpixels/sec |
| 1.89 Gpixels/sec | Feature Matching | 1.74 Gpixels/sec |
| 1150 Gpixels/sec | Stereo Matching | 871 Gpixels/sec |
| 29783 FPS | Particle Physics | 29891.2 FPS |
| OpenCL | API | OpenCL |
| 28298 | G3D Mark Score | 31406 |
| 1094 | G2D Mark | 1285 |
| 265 FPS | DirectX 11 | 356 FPS |
| 136 FPS | DirectX 12 | 133 FPS |
| 11559 Ops/s | GPU Compute | 17768 Ops/s |
| 30250 | GB6 ML Single Precision | 42092 |
| 52126 | GB6 ML Half Precision | 50673 |
| 23496 | GB6 ML Quantized | 32874 |
| 12121 | Image Classification (SP) | 18608 |
| 33054 | Image Segmentation (HP) | 25385 |
| 33652 | Image Super Resolution (Q) | 45641 |
| 67213 | Face Detection (HP) | 71321 |
| 151395 | Pose Estimation (Q) | 257258 |
| 3209 | Text Classification (SP) | 5240 |
| 6292 | Machine Translation (HP) | 7425 |
| 15618 | Object Detection (SP) | 21335 |
| 57894 | Depth Estimation (Q) | 66140 |
| 272117 | Style Transfer (SP) | 483867 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 170-242 GPixel/s | Pixel Fill Rate | 480 GPixel/s |
| 497-708 GTexel/s | Texture Fill Rate | 959 GTexel/s |
| 31.8-45.3 TFLOPS | FLOPS (FP32) | 61.4 TFLOPS |
| GDDR7 | Memory Type | GDDR6 |
| 24 GB | Memory Size | 24 GB |
| 1750 MHz | Memory Clock | 2500 MHz |
| 28000 Mbps | Effective Memory Speed | 20000 Mbps |
| 256-bit | Bus | 384-bit |
| No | ECC | No |
| 896 GB/s | Memory Bandwidth | 960 GB/s |
| PCIe 5.0 x16 | Interface | PCIe 4.0 x16 |
| 95-175 W (configurable) | TGP | 355 W |
| TSMC | Manufacturing | TSMC |
| 4 nm | Fabrication Process | 5 nm |
| 378 mm² | Die Size | 529 mm² |
| 45.6 billion | Transistor Count | 57 billion |
| 120.63 MTr/mm² | Transistor Density | 107.75 MTr/mm² |
| 12 | DirectX | 12 |
| 1.4 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.2 |
| 10.1 | CUDA | — |
| Yes | Ray Tracing | Yes |
| DLSS 4 | DLSS | No |
| 2.1a | DisplayPort | 2.1 |
| Nvidia | Vendor | Amd |
| Discrete | Build | Discrete |
| January 6, 2025 | Released | November 3, 2022 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| Blackwell 2.0 | Architecture | RDNA 3.0 |
| GB203-400 | GPU Codename | Navi 31 |
| -Intel Core Ultra 9 275HXor above | Recommended CPU | -Intel Core i7 13700Kor above |
| 26140 | Steel Nomad Lite Score | 29870 |
| 25013 | Time Spy | 30766 |
| 115677 | Solar Bay | 123758 |
| 16533 | Port Royal | 16749 |
| 51096 | Fire Strike | 73217 |
| 47099 | Wild Life Extreme | 58530 |
| 177139 | Night Raid | 184767 |
| 990-1515 MHz (configurable) | Base Clock | 1929 MHz |
| 1515-2160 MHz (configurable) | Boost Clock | 2498 MHz |
| 10496 | Shading Units | 6144 |
| 328 | Texture Mapping Units (TMUs) | 384 |
| 112 | Render Output Units (ROPs) | 192 |
| 82 | Compute Units (Pipelines) | — |
| 328 | Tensor Cores | — |
| 82 | Ray-tracing Cores | 96 |
| 128KB per cluster | L1 Cache | 256KB per cluster |
| 64MB shared | L2 Cache | 6MB shared |
| 2 IPC | Instructions Per Cycle | 4 IPC |
Compare with something else?
Compare GeForce RTX 5090 with another →