Quick/Comparisons
The GeForce RTX 5090 dominates in gaming performance, thanks to its higher score of 100. Its exceptional gaming capabilities leave the GeForce RTX 5090 Laptop far behind.
The GeForce RTX 5090 takes the lead in content creation with a score of 93, outperforming the GeForce RTX 5090 Laptop's score of 73.
The GeForce RTX 5090 excels in AI/ML compute with a score of 95, significantly outpacing the GeForce RTX 5090 Laptop's score of 60.
100 | Gaming | 71 |
93 | Workstation | 73 |
95 | AI/ML | 60 |
49 | Energy Efficiency | 50 |
96 | Quick Comparison Final Score | 67 |
| GB202-300 | Graphics Processor | GB203-400 |
| 21760 | Cores | 10496 |
| 680 / 176 | TMUs / ROPs | 328 / 112 |
| 15010.34 | Blender GPU | 8001.96 |
| 244 | Forza Horizon 5 | 154 |
| 323 | The Witcher 3 | 198 |
| 265 | Counter-Strike 2 | 213 |
| 202 | Far Cry 6 | 155 |
| 207 | Hogwarts Legacy | 123 |
| 327 | Call of Duty | 187 |
| 179 | Ghost of Tsushima | 115 |
| 229 | Cyberpunk 2077 | 155 |
| 299 | Tomb Raider | 260 |
| 253 | Average FPS | 173 |
| 294 | 1080p High | 202 |
| 253 | 1080p Ultra | 173 |
| 207 | 1440p Ultra | 137 |
| 124 | 4K Ultra | 80 |
| Low | Margin of Error | Low |
| 419309 | GB6 Compute Score | 226752 |
| 333 img/sec | Background Blur | 266.5 img/sec |
| 298.5 img/sec | Face Detection | 196.9 img/sec |
| 21.7 Gpixels/sec | Horizon Detection | 10.6 Gpixels/sec |
| 33.7 Gpixels/sec | Edge Detection | 15.2 Gpixels/sec |
| 34.5 Gpixels/sec | Gaussian Blur | 14.4 Gpixels/sec |
| 2.53 Gpixels/sec | Feature Matching | 1.89 Gpixels/sec |
| 2850 Gpixels/sec | Stereo Matching | 1150 Gpixels/sec |
| 59146.9 FPS | Particle Physics | 29783 FPS |
| OpenCL | API | OpenCL |
| 38955 | G3D Mark Score | 28298 |
| 1413 | G2D Mark | 1094 |
| 341 FPS | DirectX 11 | 265 FPS |
| 178 FPS | DirectX 12 | 136 FPS |
| 24632 Ops/s | GPU Compute | 11559 Ops/s |
| 114685 | Face Detection (HP) | 67213 |
| 344729 | Pose Estimation (Q) | 151395 |
| 4464 | Text Classification (SP) | 3209 |
| 8184 | Machine Translation (HP) | 6292 |
| 27802 | Object Detection (SP) | 15618 |
| 85572 | Depth Estimation (Q) | 57894 |
| 687080 | Style Transfer (SP) | 272117 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 53861 | GB6 ML Single Precision | 30250 |
| 81080 | GB6 ML Half Precision | 52126 |
| 38938 | GB6 ML Quantized | 23496 |
| 18948 | Image Classification (SP) | 12121 |
| 55109 | Image Segmentation (HP) | 33054 |
| 58478 | Image Super Resolution (Q) | 33652 |
| 424 GPixel/s | Pixel Fill Rate | 170-242 GPixel/s |
| 1637 GTexel/s | Texture Fill Rate | 497-708 GTexel/s |
| 104.8 TFLOPS | FLOPS (FP32) | 31.8-45.3 TFLOPS |
| GDDR7 | Memory Type | GDDR7 |
| 32 GB | Memory Size | 24 GB |
| 1750 MHz | Memory Clock | 1750 MHz |
| 28000 Mbps | Effective Memory Speed | 28000 Mbps |
| 512-bit | Bus | 256-bit |
| No | ECC | No |
| 1792 GB/s | Memory Bandwidth | 896 GB/s |
| PCIe 5.0 x16 | Interface | PCIe 5.0 x16 |
| 575 W | TGP | 95-175 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 4 nm | Fabrication Process | 4 nm |
| 750 mm² | Die Size | 378 mm² |
| 92.2 billion | Transistor Count | 45.6 billion |
| 122.93 MTr/mm² | Transistor Density | 120.63 MTr/mm² |
| 12.2 | DirectX | 12 |
| 1.4 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 12 | CUDA | 10.1 |
| Yes | Ray Tracing | Yes |
| DLSS 4 | DLSS | DLSS 4 |
| 2.1b | DisplayPort | 2.1a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 7, 2025 | Released | January 6, 2025 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| Blackwell 2.0 | Architecture | Blackwell 2.0 |
| GB202-300 | GPU Codename | GB203-400 |
| -Intel Core Ultra 9 285Kor above | Recommended CPU | -Intel Core Ultra 9 275HXor above |
| 52638 | Steel Nomad Lite Score | 26140 |
| 46941 | Time Spy | 25013 |
| 235224 | Solar Bay | 115677 |
| 38113 | Port Royal | 16533 |
| 87433 | Fire Strike | 51096 |
| 108736 | Wild Life Extreme | 47099 |
| 207058 | Night Raid | 177139 |
| 2017 MHz | Base Clock | 990-1515 MHz (configurable) |
| 2407 MHz | Boost Clock | 1515-2160 MHz (configurable) |
| 21760 | Shading Units | 10496 |
| 680 | Texture Mapping Units (TMUs) | 328 |
| 176 | Render Output Units (ROPs) | 112 |
| 170 | Compute Units (Pipelines) | 82 |
| 680 | Tensor Cores | 328 |
| 170 | Ray-tracing Cores | 82 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 96MB shared | L2 Cache | 64MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 5090 with another →