Quick/Comparisons
The Nvidia RTX Pro 6000 Blackwell takes the lead in gaming performance with a score of 99, outpacing the GeForce RTX 4090's 92.
The Nvidia RTX Pro 6000 Blackwell's perfect score of 100 in workstation performance makes it the clear winner in content creation, outdoing the GeForce RTX 4090's 91.
The Nvidia RTX Pro 6000 Blackwell's strong AI/ML compute capabilities, scoring 93, leave the GeForce RTX 4090's 76 in the dust.
92 | Gaming | 99 |
91 | Workstation | 100 |
76 | AI/ML |
Compare with something else?
Compare GeForce RTX 4090 with another →93 |
43 | Energy Efficiency | 49 |
89 | Quick Comparison Final Score | 98 |
| AD102 | Graphics Processor | GB202-300-A1 |
| 16384 | Cores | 24064 |
| 512 / 176 | TMUs / ROPs | 752 / 190 |
| 11688.48 | Blender GPU | 16644.8 |
| 203 | Forza Horizon 5 | 230 |
| 270 | The Witcher 3 | 304 |
| 245 | Counter-Strike 2 | 259 |
| 183 | Far Cry 6 | 198 |
| 165 | Hogwarts Legacy | 192 |
| 269 | Call of Duty | 301 |
| 150 | Ghost of Tsushima | 172 |
| 204 | Cyberpunk 2077 | 221 |
| 283 | Tomb Raider | 303 |
| 219 | Average FPS | 242 |
| 256 | 1080p High | 282 |
| 219 | 1080p Ultra | 242 |
| 176 | 1440p Ultra | 197 |
| 107 | 4K Ultra | 118 |
| Low | Margin of Error | High |
| 2.38 Gpixels/sec | Feature Matching | 2.47 Gpixels/sec |
| 1950 Gpixels/sec | Stereo Matching | 3040 Gpixels/sec |
| 48090.4 FPS | Particle Physics | 42574.6 FPS |
| OpenCL | API | OpenCL |
| 316301 | GB6 Compute Score | 419470 |
| 318.9 img/sec | Background Blur | 366.1 img/sec |
| 222.8 img/sec | Face Detection | 248 img/sec |
| 14.2 Gpixels/sec | Horizon Detection | 23.3 Gpixels/sec |
| 21 Gpixels/sec | Edge Detection | 35.2 Gpixels/sec |
| 23.9 Gpixels/sec | Gaussian Blur | 45 Gpixels/sec |
| 38071 | G3D Mark Score | 37305 |
| 1303 | G2D Mark | 1375 |
| 324 FPS | DirectX 11 | 338 FPS |
| 151 FPS | DirectX 12 | 153 FPS |
| 26193 Ops/s | GPU Compute | 26895 Ops/s |
| 42962 | GB6 ML Single Precision | 50053 |
| 59636 | GB6 ML Half Precision | 74036 |
| 31670 | GB6 ML Quantized | 37636 |
| 15600 | Image Classification (SP) | 16903 |
| 36657 | Image Segmentation (HP) | 48518 |
| 48114 | Image Super Resolution (Q) | 54618 |
| 78111 | Face Detection (HP) | 103224 |
| 289639 | Pose Estimation (Q) | 338587 |
| 4074 | Text Classification (SP) | 3894 |
| 6349 | Machine Translation (HP) | 7291 |
| 21186 | Object Detection (SP) | 26498 |
| 75599 | Depth Estimation (Q) | 90853 |
| 601428 | Style Transfer (SP) | 635289 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 444 GPixel/s | Pixel Fill Rate | 497 GPixel/s |
| 1290 GTexel/s | Texture Fill Rate | 1968 GTexel/s |
| 82.6 TFLOPS | FLOPS (FP32) | 126 TFLOPS |
| GDDR6X | Memory Type | GDDR7 |
| 24 GB | Memory Size | 96 GB |
| 2625 MHz | Memory Clock | 1750 MHz |
| 21000 Mbps | Effective Memory Speed | 28000 Mbps |
| 384-bit | Bus | 512-bit |
| No | ECC | Yes |
| 1010 GB/s | Memory Bandwidth | 1792 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 5.0 x16 |
| 450 W | TGP | 600 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 5 nm |
| 609 mm² | Die Size | 750 mm² |
| 76.3 billion | Transistor Count | 92.2 billion |
| 125.29 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 |
| 8.9 | CUDA | 12 |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | DLSS 4 |
| 1.4a | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| September 20, 2022 | Released | March 18, 2026 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Professional |
| High-end | Segment | High-end |
| Ada Lovelace | Architecture | Blackwell 2.0 |
| AD102 | GPU Codename | GB202-300-A1 |
| -Intel Core i9 14900Kor above | Recommended CPU | -AMD Ryzen 9 9955HX3Dor above |
| 42169 | Steel Nomad Lite Score | 50516 |
| 36311 | Time Spy | 42437 |
| 187386 | Solar Bay | 258808 |
| 26128 | Port Royal | 39952 |
| 72387 | Fire Strike | 72183 |
| 85230 | Wild Life Extreme | 110070 |
| 195880 | Night Raid | 216213 |
| 2235 MHz | Base Clock | 1590 MHz |
| 2520 MHz | Boost Clock | 2617 MHz |
| 16384 | Shading Units | 24064 |
| 512 | Texture Mapping Units (TMUs) | 752 |
| 176 | Render Output Units (ROPs) | 190 |
| 128 | Compute Units (Pipelines) | 188 |
| 512 | Tensor Cores | 752 |
| 128 | Ray-tracing Cores | 188 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 72MB shared | L2 Cache | 128MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |