Quick/Comparisons
99 | Gaming | 4 |
100 | Workstation | 12 |
93 | AI/ML |
Compare with something else?
Compare Nvidia RTX Pro with another →4 |
49 | Energy Efficiency | 84 |
98 | Quick Comparison Final Score | 20 |
| GB202-300-A1 | Graphics Processor | Raven |
| 24064 | Cores | 384 |
| 752 / 190 | TMUs / ROPs | 24 / 8 |
| 16644.8 | Blender GPU | — |
| 230 | Forza Horizon 5 | - |
| 304 | The Witcher 3 | — |
| 259 | Counter-Strike 2 | 15 |
| 198 | Far Cry 6 | 10 |
| 192 | Hogwarts Legacy | - |
| 301 | Call of Duty | 12 |
| 172 | Ghost of Tsushima | - |
| 221 | Cyberpunk 2077 | — |
| 303 | Tomb Raider | 9 |
| 242 | Average FPS | 9 |
| 282 | 1080p High | 12 |
| 242 | 1080p Ultra | 9 |
| 197 | 1440p Ultra | - |
| 118 | 4K Ultra | - |
| High | Margin of Error | Low |
| 419470 | GB6 Compute Score | 8112 |
| 366.1 img/sec | Background Blur | 17.6 img/sec |
| 248 img/sec | Face Detection | 9.06 img/sec |
| 23.3 Gpixels/sec | Horizon Detection | 0.28 Gpixels/sec |
| 35.2 Gpixels/sec | Edge Detection | 0.58 Gpixels/sec |
| 45 Gpixels/sec | Gaussian Blur | 0.38 Gpixels/sec |
| 2.47 Gpixels/sec | Feature Matching | 0.09 Gpixels/sec |
| 3040 Gpixels/sec | Stereo Matching | 27.6 Gpixels/sec |
| 42574.6 FPS | Particle Physics | 879 FPS |
| OpenCL | API | OpenCL |
| 37305 | G3D Mark Score | 1308 |
| 1375 | G2D Mark | 328 |
| 338 FPS | DirectX 11 | 9 FPS |
| 153 FPS | DirectX 12 | 6 FPS |
| 26895 Ops/s | GPU Compute | 646 Ops/s |
| 50053 | GB6 ML Single Precision | 2274 |
| 74036 | GB6 ML Half Precision | 2834 |
| 37636 | GB6 ML Quantized | 1738 |
| 16903 | Image Classification (SP) | 986 |
| 48518 | Image Segmentation (HP) | 1173 |
| 54618 | Image Super Resolution (Q) | 2200 |
| 103224 | Face Detection (HP) | 2979 |
| 338587 | Pose Estimation (Q) | 6497 |
| 3894 | Text Classification (SP) | 632 |
| 7291 | Machine Translation (HP) | 1306 |
| 26498 | Object Detection (SP) | 1093 |
| 90853 | Depth Estimation (Q) | 3935 |
| 635289 | Style Transfer (SP) | 13291 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 497 GPixel/s | Pixel Fill Rate | 9-14 GPixel/s |
| 1968 GTexel/s | Texture Fill Rate | 26-43 GTexel/s |
| 126 TFLOPS | FLOPS (FP32) | 0.8-1.4 TFLOPS |
| GDDR7 | Memory Type | System Shared |
| 96 GB | Memory Size | System RAM Dependent |
| 1750 MHz | Memory Clock | System RAM Dependent |
| 28000 Mbps | Effective Memory Speed | System RAM Dependent |
| 512-bit | Bus | — |
| Yes | ECC | No |
| 1792 GB/s | Memory Bandwidth | — |
| PCIe 5.0 x16 | Interface | IGP |
| 600 W | TGP | 15 W |
| TSMC | Manufacturing | TSMC |
| 5 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 | 1.2 |
| 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 |
| March 18, 2026 | Released | February 1, 2018 |
| Desktop | Case | Laptop |
| Professional | Purpose | Generic |
| High-end | Segment | Entry-level |
| Blackwell 2.0 | Architecture | GCN 5.0 |
| GB202-300-A1 | GPU Codename | Raven |
| -AMD Ryzen 9 9955HX3Dor above | Recommended CPU | -AMD Ryzen 5 4600Hor above |
| 50516 | Steel Nomad Lite Score | 816 |
| 42437 | Time Spy | 833 |
| 258808 | Solar Bay | — |
| 39952 | Port Royal | — |
| 72183 | Fire Strike | 2697 |
| 110070 | Wild Life Extreme | 1635 |
| 216213 | Night Raid | 11029 |
| 1590 MHz | Base Clock | 300 MHz |
| 2617 MHz | Boost Clock | 1100-1800 MHz (configurable) |
| 24064 | Shading Units | 384 |
| 752 | Texture Mapping Units (TMUs) | 24 |
| 190 | Render Output Units (ROPs) | 8 |
| 188 | Compute Units (Pipelines) | 6 |
| 752 | Tensor Cores | No |
| 188 | Ray-tracing Cores | No |
| 128KB per cluster | L1 Cache | — |
| 128MB shared | L2 Cache | — |
| 2 IPC | Instructions Per Cycle | 2 IPC |