Quick/Comparisons
The Nvidia RTX Pro 6000 Blackwell's superior gaming performance and higher benchmark scores make it the clear winner in this category. Its 99 score leaves the GeForce RTX 3090 Ti's 66 score far behind.
The Nvidia RTX Pro 6000 Blackwell's perfect score in workstation performance and strong memory capacity make it the clear winner in this category. Its 100 score leaves the GeForce RTX 3090 Ti's 73 score in second place.
The Nvidia RTX Pro 6000 Blackwell's strong AI/ML compute capabilities and high score of 93 make it the clear winner in this category. Its 93 score leaves the GeForce RTX 3090 Ti's 52 score far behind.
66 | Gaming | 99 |
73 | Workstation | 100 |
52 | AI/ML | 93 |
37 | Energy Efficiency | 49 |
66 | Quick Comparison Final Score | 98 |
| GA102 | Graphics Processor | GB202-300-A1 |
| 10752 | Cores | 24064 |
| 336 / 112 | TMUs / ROPs | 752 / 190 |
| 6057.83 | Blender GPU | 16644.8 |
| 141 | Forza Horizon 5 | 230 |
| 182 | The Witcher 3 | 304 |
| 210 | Counter-Strike 2 | 259 |
| 147 | Far Cry 6 | 198 |
| 112 | Hogwarts Legacy | 192 |
| 173 | Call of Duty | 301 |
| 108 | Ghost of Tsushima | 172 |
| 143 | Cyberpunk 2077 | 221 |
| 243 | Tomb Raider | 303 |
| 162 | Average FPS | 242 |
| 128 | 1440p Ultra | 197 |
| 75 | 4K Ultra | 118 |
| Low | Margin of Error | High |
| 193 | 1080p High | 282 |
| 162 | 1080p Ultra | 242 |
| 232083 | GB6 Compute Score | 419470 |
| 362.7 img/sec | Background Blur | 366.1 img/sec |
| 227.9 img/sec | Face Detection | 248 img/sec |
| 11.3 Gpixels/sec | Horizon Detection | 23.3 Gpixels/sec |
| 15.9 Gpixels/sec | Edge Detection | 35.2 Gpixels/sec |
| 12.1 Gpixels/sec | Gaussian Blur | 45 Gpixels/sec |
| 1.56 Gpixels/sec | Feature Matching | 2.47 Gpixels/sec |
| 1080 Gpixels/sec | Stereo Matching | 3040 Gpixels/sec |
| 31024.6 FPS | Particle Physics | 42574.6 FPS |
| OpenCL | API | OpenCL |
| 29288 | G3D Mark Score | 37305 |
| 1226 | G2D Mark | 1375 |
| 238 FPS | DirectX 11 | 338 FPS |
| 122 FPS | DirectX 12 | 153 FPS |
| 16569 Ops/s | GPU Compute | 26895 Ops/s |
| 26701 | GB6 ML Single Precision | 50053 |
| 38573 | GB6 ML Half Precision | 74036 |
| 15995 | GB6 ML Quantized | 37636 |
| 10246 | Image Classification (SP) | 16903 |
| 22830 | Image Segmentation (HP) | 48518 |
| 23532 | Image Super Resolution (Q) | 54618 |
| 48657 | Face Detection (HP) | 103224 |
| 147241 | Pose Estimation (Q) | 338587 |
| 2917 | Text Classification (SP) | 3894 |
| 4427 | Machine Translation (HP) | 7291 |
| 13323 | Object Detection (SP) | 26498 |
| 40055 | Depth Estimation (Q) | 90853 |
| 298683 | Style Transfer (SP) | 635289 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 208 GPixel/s | Pixel Fill Rate | 497 GPixel/s |
| 625 GTexel/s | Texture Fill Rate | 1968 GTexel/s |
| 40 TFLOPS | FLOPS (FP32) | 126 TFLOPS |
| GDDR6X | Memory Type | GDDR7 |
| 24 GB | Memory Size | 96 GB |
| 1313 MHz | Memory Clock | 1750 MHz |
| 21000 Mbps | Effective Memory Speed | 28000 Mbps |
| 384-bit | Bus | 512-bit |
| No | ECC | Yes |
| 1008 GB/s | Memory Bandwidth | 1792 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 5.0 x16 |
| 450 W | TGP | 600 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 5 nm |
| 628 mm² | Die Size | 750 mm² |
| 28 billion | Transistor Count | 92.2 billion |
| 44.59 MTr/mm² | Transistor Density | 122.93 MTr/mm² |
| 12 | DirectX | 12.2 |
| 1.3 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.6 | CUDA | 12 |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | DLSS 4 |
| 1.4a | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| March 29, 2022 | Released | March 18, 2026 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Professional |
| High-end | Segment | High-end |
| Ampere | Architecture | Blackwell 2.0 |
| GA102 | GPU Codename | GB202-300-A1 |
| -Intel Core i9 12900Kor above | Recommended CPU | -AMD Ryzen 9 9955HX3Dor above |
| 24378 | Steel Nomad Lite Score | 50516 |
| 21854 | Time Spy | 42437 |
| 109167 | Solar Bay | 258808 |
| 14888 | Port Royal | 39952 |
| 51943 | Fire Strike | 72183 |
| 48864 | Wild Life Extreme | 110070 |
| 156500 | Night Raid | 216213 |
| 1560 MHz | Base Clock | 1590 MHz |
| 1860 MHz | Boost Clock | 2617 MHz |
| 10752 | Shading Units | 24064 |
| 336 | Texture Mapping Units (TMUs) | 752 |
| 112 | Render Output Units (ROPs) | 190 |
| 84 | Compute Units (Pipelines) | 188 |
| 336 | Tensor Cores | 752 |
| 84 | Ray-tracing Cores | 188 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 6MB shared | L2 Cache | 128MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 3090 with another →