Quick/Comparisons
The GeForce RTX 5090 dominates gaming performance with a perfect score, thanks to its Blackwell 2.0 architecture and 32GB GDDR7 memory.
The GeForce RTX 5090's strong workstation performance and 93 score give it the edge in content creation, outpacing the Nvidia RTX A5000 Laptop's 51 score.
The GeForce RTX 5090's capable AI/ML compute and 95 score make it the winner in AI & Machine Learning, leaving the Nvidia RTX A5000 Laptop's 33 score far behind.
100 | Gaming | 33 |
93 | Workstation | 51 |
95 | AI/ML | 33 |
49 | Energy Efficiency | 39 |
96 | Quick Comparison Final Score | 39 |
| GB202-300 | Graphics Processor | GA104 |
| 21760 | Cores | 6144 |
| 680 / 176 | TMUs / ROPs | 192 / 96 |
| 15010.34 | Blender GPU | 2928.42 |
| 244 | Forza Horizon 5 | 72 |
| 323 | The Witcher 3 | 104 |
| 265 | Counter-Strike 2 | 140 |
| 202 | Far Cry 6 | 89 |
| 207 | Hogwarts Legacy | 57 |
| 327 | Call of Duty | 77 |
| 179 | Ghost of Tsushima | 54 |
| 229 | Cyberpunk 2077 | 67 |
| 299 | Tomb Raider | 103 |
| 253 | Average FPS | 85 |
| 294 | 1080p High | 104 |
| 253 | 1080p Ultra | 85 |
| 207 | 1440p Ultra | 62 |
| 124 | 4K Ultra | 34 |
| Low | Margin of Error | High |
| 419309 | GB6 Compute Score | 111855 |
| 333 img/sec | Background Blur | 172.7 img/sec |
| 298.5 img/sec | Face Detection | 103.8 img/sec |
| 21.7 Gpixels/sec | Horizon Detection | 5.34 Gpixels/sec |
| 33.7 Gpixels/sec | Edge Detection | 7.2 Gpixels/sec |
| 34.5 Gpixels/sec | Gaussian Blur | 5.61 Gpixels/sec |
| 2.53 Gpixels/sec | Feature Matching | 1.05 Gpixels/sec |
| 2850 Gpixels/sec | Stereo Matching | 474.4 Gpixels/sec |
| 59146.9 FPS | Particle Physics | 14218.2 FPS |
| OpenCL | API | OpenCL |
| 38955 | G3D Mark Score | 16426 |
| 1413 | G2D Mark | 663 |
| 341 FPS | DirectX 11 | 138 FPS |
| 178 FPS | DirectX 12 | 75 FPS |
| 24632 Ops/s | GPU Compute | 7003 Ops/s |
| 114685 | Face Detection (HP) | 30795 |
| 344729 | Pose Estimation (Q) | 71291 |
| 4464 | Text Classification (SP) | 2115 |
| 8184 | Machine Translation (HP) | 3207 |
| 27802 | Object Detection (SP) | 8583 |
| 85572 | Depth Estimation (Q) | 25256 |
| 687080 | Style Transfer (SP) | 149822 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 53861 | GB6 ML Single Precision | 15655 |
| 81080 | GB6 ML Half Precision | 24490 |
| 38938 | GB6 ML Quantized | 10684 |
| 18948 | Image Classification (SP) | 6590 |
| 55109 | Image Segmentation (HP) | 12226 |
| 58478 | Image Super Resolution (Q) | 16682 |
| 424 GPixel/s | Pixel Fill Rate | 120-170 GPixel/s |
| 1637 GTexel/s | Texture Fill Rate | 239-340 GTexel/s |
| 104.8 TFLOPS | FLOPS (FP32) | 15.3-21.7 TFLOPS |
| GDDR7 | Memory Type | GDDR6 |
| 32 GB | Memory Size | 16 GB |
| 1750 MHz | Memory Clock | 1750 MHz |
| 28000 Mbps | Effective Memory Speed | 14000 Mbps |
| 512-bit | Bus | 256-bit |
| No | ECC | Yes |
| 1792 GB/s | Memory Bandwidth | 448 GB/s |
| PCIe 5.0 x16 | Interface | PCIe 4.0 x16 |
| 575 W | TGP | 80-165 W (configurable) |
| TSMC | Manufacturing | Samsung |
| 4 nm | Fabrication Process | 8 nm |
| 750 mm² | Die Size | 392 mm² |
| 92.2 billion | Transistor Count | 17.4 billion |
| 122.93 MTr/mm² | Transistor Density | 44.39 MTr/mm² |
| 12.2 | DirectX | 12 |
| 1.4 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 12 | CUDA | 8.6 |
| Yes | Ray Tracing | Yes |
| DLSS 4 | DLSS | DLSS 2 |
| 2.1b | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 7, 2025 | Released | April 12, 2021 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Professional |
| High-end | Segment | High-end |
| Blackwell 2.0 | Architecture | Ampere |
| GB202-300 | GPU Codename | GA104 |
| -Intel Core Ultra 9 285Kor above | Recommended CPU | -Intel Core i9 12900HXor above |
| 52638 | Steel Nomad Lite Score | 9479 |
| 46941 | Time Spy | 9291 |
| 235224 | Solar Bay | 43275 |
| 38113 | Port Royal | 5797 |
| 87433 | Fire Strike | 25901 |
| 108736 | Wild Life Extreme | 20653 |
| 207058 | Night Raid | 61009 |
| 2017 MHz | Base Clock | 780-1215 MHz (configurable) |
| 2407 MHz | Boost Clock | 1245-1770 MHz (configurable) |
| 21760 | Shading Units | 6144 |
| 680 | Texture Mapping Units (TMUs) | 192 |
| 176 | Render Output Units (ROPs) | 96 |
| 170 | Compute Units (Pipelines) | 48 |
| 680 | Tensor Cores | 192 |
| 170 | Ray-tracing Cores | 48 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 96MB shared | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 5090 with another →