Quick/Comparisons
The Nvidia RTX Pro 6000 Blackwell's superior gaming performance is evident, with a 36-point lead over the GeForce RTX 4090 Laptop.
The Nvidia RTX Pro 6000 Blackwell's perfect score in workstation performance makes it the clear winner for content creation tasks.
Although the GeForce RTX 4090 Laptop has a respectable AI/ML score, the Nvidia RTX Pro 6000 Blackwell's 38-point lead gives it the edge in this use case.
63 | Gaming | 99 |
63 | Workstation | 100 |
55 | AI/ML |
Compare with something else?
Compare GeForce RTX 4090 with another →93 |
45 | Energy Efficiency | 49 |
59 | Quick Comparison Final Score | 98 |
| AD103 (GN21-X11) | Graphics Processor | GB202-300-A1 |
| 9728 | Cores | 24064 |
| 304 / 112 | TMUs / ROPs | 752 / 190 |
| 7059.06 | Blender GPU | 16644.8 |
| 131 | Forza Horizon 5 | 230 |
| 182 | The Witcher 3 | 304 |
| 208 | Counter-Strike 2 | 259 |
| 147 | Far Cry 6 | 198 |
| 108 | Hogwarts Legacy | 192 |
| 164 | Call of Duty | 301 |
| 100 | Ghost of Tsushima | 172 |
| 137 | Cyberpunk 2077 | 221 |
| 231 | Tomb Raider | 303 |
| 156 | Average FPS | 242 |
| 187 | 1080p High | 282 |
| 156 | 1080p Ultra | 242 |
| 123 | 1440p Ultra | 197 |
| 72 | 4K Ultra | 118 |
| Low | Margin of Error | High |
| 203263 | GB6 Compute Score | 419470 |
| 264 img/sec | Background Blur | 366.1 img/sec |
| 134.3 img/sec | Face Detection | 248 img/sec |
| 9.27 Gpixels/sec | Horizon Detection | 23.3 Gpixels/sec |
| 12.7 Gpixels/sec | Edge Detection | 35.2 Gpixels/sec |
| 13.2 Gpixels/sec | Gaussian Blur | 45 Gpixels/sec |
| 1.92 Gpixels/sec | Feature Matching | 2.47 Gpixels/sec |
| 1060 Gpixels/sec | Stereo Matching | 3040 Gpixels/sec |
| 29225.1 FPS | Particle Physics | 42574.6 FPS |
| OpenCL | API | OpenCL |
| 27060 | G3D Mark Score | 37305 |
| 988 | G2D Mark | 1375 |
| 258 FPS | DirectX 11 | 338 FPS |
| 106 FPS | DirectX 12 | 153 FPS |
| 12206 Ops/s | GPU Compute | 26895 Ops/s |
| 29362 | GB6 ML Single Precision | 50053 |
| 42611 | GB6 ML Half Precision | 74036 |
| 22212 | GB6 ML Quantized | 37636 |
| 11346 | Image Classification (SP) | 16903 |
| 24625 | Image Segmentation (HP) | 48518 |
| 36874 | Image Super Resolution (Q) | 54618 |
| 50088 | Face Detection (HP) | 103224 |
| 174844 | Pose Estimation (Q) | 338587 |
| 3226 | Text Classification (SP) | 3894 |
| 4905 | Machine Translation (HP) | 7291 |
| 14667 | Object Detection (SP) | 26498 |
| 53868 | Depth Estimation (Q) | 90853 |
| 340056 | Style Transfer (SP) | 635289 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 163-228 GPixel/s | Pixel Fill Rate | 497 GPixel/s |
| 442-620 GTexel/s | Texture Fill Rate | 1968 GTexel/s |
| 28.3-39.7 TFLOPS | FLOPS (FP32) | 126 TFLOPS |
| GDDR6 | Memory Type | GDDR7 |
| 16 GB | Memory Size | 96 GB |
| 2000 MHz | Memory Clock | 1750 MHz |
| 16000 Mbps | Effective Memory Speed | 28000 Mbps |
| 256-bit | Bus | 512-bit |
| No | ECC | Yes |
| 512 GB/s | Memory Bandwidth | 1792 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 5.0 x16 |
| 80-175 W (configurable) | TGP | 600 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 5 nm |
| 379 mm² | Die Size | 750 mm² |
| 45.9 billion | Transistor Count | 92.2 billion |
| 121.11 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 |
| February 8, 2023 | Released | March 18, 2026 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Professional |
| High-end | Segment | High-end |
| Ada Lovelace | Architecture | Blackwell 2.0 |
| AD103 (GN21-X11) | GPU Codename | GB202-300-A1 |
| -Intel Core Ultra 9 185Hor above | Recommended CPU | -AMD Ryzen 9 9955HX3Dor above |
| 22501 | Steel Nomad Lite Score | 50516 |
| 21401 | Time Spy | 42437 |
| 96130 | Solar Bay | 258808 |
| 13733 | Port Royal | 39952 |
| 45218 | Fire Strike | 72183 |
| 42491 | Wild Life Extreme | 110070 |
| 147892 | Night Raid | 216213 |
| 930-1620 MHz (configurable) | Base Clock | 1590 MHz |
| 1455-2040 MHz (configurable) | Boost Clock | 2617 MHz |
| 9728 | Shading Units | 24064 |
| 304 | Texture Mapping Units (TMUs) | 752 |
| 112 | Render Output Units (ROPs) | 190 |
| 76 | Compute Units (Pipelines) | 188 |
| 304 | Tensor Cores | 752 |
| 76 | Ray-tracing Cores | 188 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 64MB shared | L2 Cache | 128MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |