Quick/Comparisons
73 | Gaming | 9 |
82 | Workstation | 12 |
54 | AI/ML |
Compare with something else?
Compare Nvidia RTX 5000 with another →13 |
45 | Energy Efficiency | 86 |
73 | Quick Comparison Final Score | 23 |
| AD102 | Graphics Processor | Krackan Point |
| 12800 | Cores | 512 |
| 400 / 176 | TMUs / ROPs | 32 / 16 |
| 7348.98 | Blender GPU | 193.82 |
| 146 | Forza Horizon 5 | 24 |
| 186 | The Witcher 3 | 18 |
| 213 | Counter-Strike 2 | 26 |
| 151 | Far Cry 6 | 26 |
| 117 | Hogwarts Legacy | 12 |
| 179 | Call of Duty | 27 |
| 108 | Ghost of Tsushima | 12 |
| 148 | Cyberpunk 2077 | 13 |
| 242 | Tomb Raider | 22 |
| 166 | Average FPS | 20 |
| 196 | 1080p High | 26 |
| 166 | 1080p Ultra | 20 |
| 132 | 1440p Ultra | 14 |
| 78 | 4K Ultra | - |
| High | Margin of Error | Low |
| 260099 | GB6 Compute Score | 22911 |
| 286.6 img/sec | Background Blur | 57.2 img/sec |
| 220.4 img/sec | Face Detection | 30.5 img/sec |
| 9.93 Gpixels/sec | Horizon Detection | 0.83 Gpixels/sec |
| 13.7 Gpixels/sec | Edge Detection | 1.16 Gpixels/sec |
| 18.9 Gpixels/sec | Gaussian Blur | 0.93 Gpixels/sec |
| 2.2 Gpixels/sec | Feature Matching | 0.35 Gpixels/sec |
| 1580 Gpixels/sec | Stereo Matching | 97.8 Gpixels/sec |
| 41235.6 FPS | Particle Physics | 3933.5 FPS |
| OpenCL | API | OpenCL |
| 30196 | G3D Mark Score | 4877 |
| 998 | G2D Mark | 916 |
| 273 FPS | DirectX 11 | 37 FPS |
| 106 FPS | DirectX 12 | 24 FPS |
| 20736 Ops/s | GPU Compute | 2421 Ops/s |
| 24715 | GB6 ML Single Precision | 6947 |
| 36753 | GB6 ML Half Precision | 10338 |
| 19649 | GB6 ML Quantized | 5334 |
| 9943 | Image Classification (SP) | 2022 |
| 19696 | Image Segmentation (HP) | 3987 |
| 32252 | Image Super Resolution (Q) | 6657 |
| 43098 | Face Detection (HP) | 10337 |
| 138689 | Pose Estimation (Q) | 28437 |
| 2893 | Text Classification (SP) | 2326 |
| 4064 | Machine Translation (HP) | 4011 |
| 12467 | Object Detection (SP) | 1995 |
| 50352 | Depth Estimation (Q) | 12031 |
| 265482 | Style Transfer (SP) | 56710 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 449 GPixel/s | Pixel Fill Rate | 48 GPixel/s |
| 1020 GTexel/s | Texture Fill Rate | 96 GTexel/s |
| 65.3 TFLOPS | FLOPS (FP32) | 3.1 TFLOPS |
| GDDR6 | Memory Type | System Shared |
| 32 GB | Memory Size | — |
| 2250 MHz | Memory Clock | — |
| 18000 Mbps | Effective Memory Speed | — |
| 256-bit | Bus | — |
| No | ECC | — |
| 576 GB/s | Memory Bandwidth | — |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 250 W | TGP | 15-54 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 4 nm |
| 609 mm² | Die Size | 233 mm² |
| 76 billion | Transistor Count | 34 billion |
| 124.79 MTr/mm² | Transistor Density | 145.92 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.1 |
| 8.9 | CUDA | No |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| August 9, 2023 | Released | January 7, 2025 |
| Desktop | Case | Laptop |
| Professional | Purpose | Generic |
| High-end | Segment | Mid-range |
| Ada Lovelace | Architecture | RDNA 3.5 |
| AD102 | GPU Codename | Krackan Point |
| -Intel Core i9 14900Kor above | Recommended CPU | -AMD Ryzen AI 7 350or above |
| 29190 | Steel Nomad Lite Score | 2112 |
| 18675 | Time Spy | 2565 |
| 128428 | Solar Bay | 11270 |
| 17754 | Port Royal | 1103 |
| 62027 | Fire Strike | 6835 |
| 52866 | Wild Life Extreme | 5150 |
| 210443 | Night Raid | 29003 |
| 1155 MHz | Base Clock | 600 MHz |
| 2550 MHz | Boost Clock | 3000 MHz |
| 12800 | Shading Units | 512 |
| 400 | Texture Mapping Units (TMUs) | 32 |
| 176 | Render Output Units (ROPs) | 16 |
| 100 | Compute Units (Pipelines) | 8 |
| 400 | Tensor Cores | No |
| 100 | Ray-tracing Cores | 8 |
| 128KB per cluster | L1 Cache | 512KB per cluster |
| 72MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |