Quick/Comparisons
100 | Gaming | 6 |
93 | Workstation | 12 |
95 | AI/ML |
Compare with something else?
Compare GeForce RTX 5090 with another →4 |
49 | Energy Efficiency | 84 |
96 | Quick Comparison Final Score | 20 |
| GB202-300 | Graphics Processor | Raven |
| 21760 | Cores | 512 |
| 680 / 176 | TMUs / ROPs | 32 / 8 |
| 15010.34 | Blender GPU | — |
| 244 | Forza Horizon 5 | 13 |
| 323 | The Witcher 3 | 10 |
| 265 | Counter-Strike 2 | 15 |
| 202 | Far Cry 6 | 16 |
| 207 | Hogwarts Legacy | - |
| 327 | Call of Duty | 16 |
| 179 | Ghost of Tsushima | 9 |
| 229 | Cyberpunk 2077 | 9 |
| 299 | Tomb Raider | 16 |
| 253 | Average FPS | 12 |
| 294 | 1080p High | 16 |
| 253 | 1080p Ultra | 12 |
| 207 | 1440p Ultra | 9 |
| 124 | 4K Ultra | - |
| Low | Margin of Error | Low |
| 419309 | GB6 Compute Score | 10472 |
| 333 img/sec | Background Blur | 21.2 img/sec |
| 298.5 img/sec | Face Detection | 10.9 img/sec |
| 21.7 Gpixels/sec | Horizon Detection | 0.34 Gpixels/sec |
| 33.7 Gpixels/sec | Edge Detection | 0.65 Gpixels/sec |
| 34.5 Gpixels/sec | Gaussian Blur | 0.51 Gpixels/sec |
| 2.53 Gpixels/sec | Feature Matching | 0.13 Gpixels/sec |
| 2850 Gpixels/sec | Stereo Matching | 34.9 Gpixels/sec |
| 59146.9 FPS | Particle Physics | 1322.9 FPS |
| OpenCL | API | OpenCL |
| 38955 | G3D Mark Score | 1566 |
| 1413 | G2D Mark | 400 |
| 341 FPS | DirectX 11 | 10 FPS |
| 178 FPS | DirectX 12 | 8 FPS |
| 24632 Ops/s | GPU Compute | 863 Ops/s |
| 114685 | Face Detection (HP) | 2819 |
| 344729 | Pose Estimation (Q) | 7106 |
| 4464 | Text Classification (SP) | 832 |
| 8184 | Machine Translation (HP) | 1021 |
| 27802 | Object Detection (SP) | 1040 |
| 85572 | Depth Estimation (Q) | 3885 |
| 687080 | Style Transfer (SP) | 14495 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 53861 | GB6 ML Single Precision | 2257 |
| 81080 | GB6 ML Half Precision | 2817 |
| 38938 | GB6 ML Quantized | 1643 |
| 18948 | Image Classification (SP) | 924 |
| 55109 | Image Segmentation (HP) | 1148 |
| 58478 | Image Super Resolution (Q) | 2211 |
| 424 GPixel/s | Pixel Fill Rate | 9-17 GPixel/s |
| 1637 GTexel/s | Texture Fill Rate | 35-67 GTexel/s |
| 104.8 TFLOPS | FLOPS (FP32) | 1.1-2.2 TFLOPS |
| GDDR7 | Memory Type | System Shared |
| 32 GB | Memory Size | System RAM Dependent |
| 1750 MHz | Memory Clock | System RAM Dependent |
| 28000 Mbps | Effective Memory Speed | System RAM Dependent |
| 512-bit | Bus | — |
| No | ECC | No |
| 1792 GB/s | Memory Bandwidth | — |
| PCIe 5.0 x16 | Interface | IGP |
| 575 W | TGP | 15 W |
| TSMC | Manufacturing | TSMC |
| 4 nm | Fabrication Process | 7 nm |
| 750 mm² | Die Size | 210 mm² |
| 92.2 billion | Transistor Count | 4.94 billion |
| 122.93 MTr/mm² | Transistor Density | 23.52 MTr/mm² |
| 12.2 | DirectX | 12 |
| 1.4 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2 |
| 12 | CUDA | — |
| Yes | Ray Tracing | No |
| DLSS 4 | DLSS | No |
| 2.1b | DisplayPort | — |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| January 7, 2025 | Released | February 13, 2018 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Generic |
| High-end | Segment | Entry-level |
| Blackwell 2.0 | Architecture | GCN 5.0 |
| GB202-300 | GPU Codename | Raven |
| -Intel Core Ultra 9 285Kor above | Recommended CPU | -AMD Ryzen 7 4800Uor above |
| 52638 | Steel Nomad Lite Score | 1260 |
| 46941 | Time Spy | 1410 |
| 235224 | Solar Bay | — |
| 38113 | Port Royal | — |
| 87433 | Fire Strike | 4499 |
| 108736 | Wild Life Extreme | 2532 |
| 207058 | Night Raid | 17993 |
| 2017 MHz | Base Clock | 300 MHz |
| 2407 MHz | Boost Clock | 1100-2100 MHz (configurable) |
| 21760 | Shading Units | 512 |
| 680 | Texture Mapping Units (TMUs) | 32 |
| 176 | Render Output Units (ROPs) | 8 |
| 170 | Compute Units (Pipelines) | 8 |
| 680 | Tensor Cores | No |
| 170 | Ray-tracing Cores | No |
| 128KB per cluster | L1 Cache | — |
| 96MB shared | L2 Cache | — |
| 2 IPC | Instructions Per Cycle | 2 IPC |