Quick/Comparisons
The GeForce RTX 5090 outperforms the GeForce RTX 5060 Ti (8GB) in gaming by a significant margin, thanks to its superior architecture and 32GB GDDR7 memory.
The GeForce RTX 5090 excels in content creation with its strong workstation performance and 32GB GDDR7 memory, making it the better choice for professionals.
The GeForce RTX 5090's capable AI/ML compute and 32GB GDDR7 memory give it a significant edge over the GeForce RTX 5060 Ti (8GB) in AI and machine learning tasks.
50 | Gaming | 100 |
47 | Workstation | 93 |
42 | AI/ML | 95 |
48 | Energy Efficiency | 49 |
48 | Quick Comparison Final Score | 96 |
| GB206-300 | Graphics Processor | GB202-300 |
| 4608 | Cores | 21760 |
| 144 / 48 | TMUs / ROPs | 680 / 176 |
| 4313.42 | Blender GPU | 15010.34 |
| 104 | Forza Horizon 5 | 244 |
| 147 | The Witcher 3 | 323 |
| 205 | Counter-Strike 2 | 265 |
| 125 | Far Cry 6 | 202 |
| 90 | Hogwarts Legacy | 207 |
| 131 | Call of Duty | 327 |
| 81 | Ghost of Tsushima | 179 |
| 106 | Cyberpunk 2077 | 229 |
| 171 | Tomb Raider | 299 |
| 129 | Average FPS | 253 |
| 155 | 1080p High | 294 |
| 129 | 1080p Ultra | 253 |
| 99 | 1440p Ultra | 207 |
| 57 | 4K Ultra | 124 |
| Low | Margin of Error | Low |
| 141028 | GB6 Compute Score | 419309 |
| 197.7 img/sec | Background Blur | 333 img/sec |
| 131.5 img/sec | Face Detection | 298.5 img/sec |
| 5.28 Gpixels/sec | Horizon Detection | 21.7 Gpixels/sec |
| 6.79 Gpixels/sec | Edge Detection | 33.7 Gpixels/sec |
| 7.74 Gpixels/sec | Gaussian Blur | 34.5 Gpixels/sec |
| 1.53 Gpixels/sec | Feature Matching | 2.53 Gpixels/sec |
| 726.7 Gpixels/sec | Stereo Matching | 2850 Gpixels/sec |
| 21833.6 FPS | Particle Physics | 59146.9 FPS |
| OpenCL | API | OpenCL |
| 22659 | G3D Mark Score | 38955 |
| 1212 | G2D Mark | 1413 |
| 219 FPS | DirectX 11 | 341 FPS |
| 89 FPS | DirectX 12 | 178 FPS |
| 11327 Ops/s | GPU Compute | 24632 Ops/s |
| 23734 | GB6 ML Single Precision | 53861 |
| 43218 | GB6 ML Half Precision | 81080 |
| 18191 | GB6 ML Quantized | 38938 |
| 9511 | Image Classification (SP) | 18948 |
| 29012 | Image Segmentation (HP) | 55109 |
| 25621 | Image Super Resolution (Q) | 58478 |
| 52204 | Face Detection (HP) | 114685 |
| 122234 | Pose Estimation (Q) | 344729 |
| 3209 | Text Classification (SP) | 4464 |
| 6074 | Machine Translation (HP) | 8184 |
| 12095 | Object Detection (SP) | 27802 |
| 45666 | Depth Estimation (Q) | 85572 |
| 182591 | Style Transfer (SP) | 687080 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 123 GPixel/s | Pixel Fill Rate | 424 GPixel/s |
| 370 GTexel/s | Texture Fill Rate | 1637 GTexel/s |
| 23.7 TFLOPS | FLOPS (FP32) | 104.8 TFLOPS |
| GDDR7 | Memory Type | GDDR7 |
| 8 GB | Memory Size | 32 GB |
| 1750 MHz | Memory Clock | 1750 MHz |
| 28000 Mbps | Effective Memory Speed | 28000 Mbps |
| 128-bit | Bus | 512-bit |
| No | ECC | No |
| 448 GB/s | Memory Bandwidth | 1792 GB/s |
| PCIe 5.0 x8 | Interface | PCIe 5.0 x16 |
| 180 W | TGP | 575 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 4 nm |
| 181 mm² | Die Size | 750 mm² |
| 21.9 billion | Transistor Count | 92.2 billion |
| 120.99 MTr/mm² | Transistor Density | 122.93 MTr/mm² |
| 12.2 | DirectX | 12.2 |
| 1.4 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 12 | CUDA | 12 |
| Yes | Ray Tracing | Yes |
| DLSS 4 | DLSS | DLSS 4 |
| 2.1b | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| April 15, 2025 | Released | January 7, 2025 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Blackwell 2.0 | Architecture | Blackwell 2.0 |
| GB206-300 | GPU Codename | GB202-300 |
| -Intel Core Ultra 5 245Kor above | Recommended CPU | -Intel Core Ultra 9 285Kor above |
| 16172 | Steel Nomad Lite Score | 52638 |
| 15835 | Time Spy | 46941 |
| 75721 | Solar Bay | 235224 |
| 10077 | Port Royal | 38113 |
| 41970 | Fire Strike | 87433 |
| 30331 | Wild Life Extreme | 108736 |
| 140626 | Night Raid | 207058 |
| 2407 MHz | Base Clock | 2017 MHz |
| 2572 MHz | Boost Clock | 2407 MHz |
| 4608 | Shading Units | 21760 |
| 144 | Texture Mapping Units (TMUs) | 680 |
| 48 | Render Output Units (ROPs) | 176 |
| 36 | Compute Units (Pipelines) | 170 |
| 144 | Tensor Cores | 680 |
| 36 | Ray-tracing Cores | 170 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 32MB shared | L2 Cache | 96MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 5060 with another →