Quick/Comparisons
99 | Gaming | 14 |
100 | Workstation | 21 |
93 | AI/ML |
Compare with something else?
Compare Nvidia RTX Pro with another →11 |
49 | Energy Efficiency | 68 |
98 | Quick Comparison Final Score | 25 |
| GB202-300-A1 | Graphics Processor | TU117 |
| 24064 | Cores | 896 |
| 752 / 190 | TMUs / ROPs | 56 / 32 |
| 16644.8 | Blender GPU | 417.51 |
| 230 | Forza Horizon 5 | — |
| 304 | The Witcher 3 | — |
| 259 | Counter-Strike 2 | — |
| 198 | Far Cry 6 | — |
| 192 | Hogwarts Legacy | — |
| 301 | Call of Duty | — |
| 172 | Ghost of Tsushima | — |
| 221 | Cyberpunk 2077 | — |
| 303 | Tomb Raider | — |
| 242 | Average FPS | — |
| 282 | 1080p High | — |
| 242 | 1080p Ultra | — |
| 197 | 1440p Ultra | — |
| 118 | 4K Ultra | — |
| High | Margin of Error | — |
| 419470 | GB6 Compute Score | 33110 |
| 366.1 img/sec | Background Blur | 61.6 img/sec |
| 248 img/sec | Face Detection | 31.3 img/sec |
| 23.3 Gpixels/sec | Horizon Detection | 1.17 Gpixels/sec |
| 35.2 Gpixels/sec | Edge Detection | 1.48 Gpixels/sec |
| 45 Gpixels/sec | Gaussian Blur | 1.8 Gpixels/sec |
| 2.47 Gpixels/sec | Feature Matching | 0.43 Gpixels/sec |
| 3040 Gpixels/sec | Stereo Matching | 149.1 Gpixels/sec |
| 42574.6 FPS | Particle Physics | 4185.6 FPS |
| OpenCL | API | OpenCL |
| 37305 | G3D Mark Score | 7038 |
| 1375 | G2D Mark | 482 |
| 338 FPS | DirectX 11 | 51 FPS |
| 153 FPS | DirectX 12 | 32 FPS |
| 26895 Ops/s | GPU Compute | 2678 Ops/s |
| 50053 | GB6 ML Single Precision | 6235 |
| 74036 | GB6 ML Half Precision | 4946 |
| 37636 | GB6 ML Quantized | 4599 |
| 16903 | Image Classification (SP) | 2490 |
| 48518 | Image Segmentation (HP) | 3507 |
| 54618 | Image Super Resolution (Q) | 6427 |
| 103224 | Face Detection (HP) | 5241 |
| 338587 | Pose Estimation (Q) | 21102 |
| 3894 | Text Classification (SP) | 1520 |
| 7291 | Machine Translation (HP) | 2350 |
| 26498 | Object Detection (SP) | 2982 |
| 90853 | Depth Estimation (Q) | 10665 |
| 635289 | Style Transfer (SP) | 43183 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 497 GPixel/s | Pixel Fill Rate | 45 GPixel/s |
| 1968 GTexel/s | Texture Fill Rate | 78 GTexel/s |
| 126 TFLOPS | FLOPS (FP32) | 2.5 TFLOPS |
| GDDR7 | Memory Type | GDDR6 |
| 96 GB | Memory Size | 4 GB |
| 1750 MHz | Memory Clock | 1250 MHz |
| 28000 Mbps | Effective Memory Speed | 10000 Mbps |
| 512-bit | Bus | 128-bit |
| Yes | ECC | — |
| 1792 GB/s | Memory Bandwidth | 160 GB/s |
| PCIe 5.0 x16 | Interface | PCIe 3.0 x16 |
| 600 W | TGP | 40 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 12 nm |
| 750 mm² | Die Size | 200 mm² |
| 92.2 billion | Transistor Count | 4.7 billion |
| 122.93 MTr/mm² | Transistor Density | 23.5 MTr/mm² |
| 12.2 | DirectX | 12 |
| 1.4 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 12 | CUDA | 7.5 |
| Yes | Ray Tracing | No |
| DLSS 4 | DLSS | No |
| 2.1b | DisplayPort | 1.4 |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| March 18, 2026 | Released | April 12, 2021 |
| Desktop | Case | Laptop |
| Professional | Purpose | Professional |
| High-end | Segment | Entry-level |
| Blackwell 2.0 | Architecture | Turing |
| GB202-300-A1 | GPU Codename | TU117 |
| -AMD Ryzen 9 9955HX3Dor above | Recommended CPU | -Intel Core i7 11800Hor above |
| 50516 | Steel Nomad Lite Score | — |
| 42437 | Time Spy | — |
| 258808 | Solar Bay | — |
| 39952 | Port Royal | — |
| 72183 | Fire Strike | — |
| 110070 | Wild Life Extreme | — |
| 216213 | Night Raid | — |
| 1590 MHz | Base Clock | 930 MHz |
| 2617 MHz | Boost Clock | 1395 MHz |
| 24064 | Shading Units | 896 |
| 752 | Texture Mapping Units (TMUs) | 56 |
| 190 | Render Output Units (ROPs) | 32 |
| 188 | Compute Units (Pipelines) | 14 |
| 752 | Tensor Cores | — |
| 188 | Ray-tracing Cores | — |
| 128KB per cluster | L1 Cache | 64KB per cluster |
| 128MB shared | L2 Cache | 1MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |