Quick/Comparisons
The Nvidia RTX Pro 6000 Blackwell's exceptional gaming performance and high frame rates make it the clear winner in this category, outscoring the GeForce RTX 5090 Laptop by 28 points.
The Nvidia RTX Pro 6000 Blackwell's perfect score in workstation performance and strong content creation capabilities make it the clear winner in this category, outscoring the GeForce RTX 5090 Laptop by 27 points.
The Nvidia RTX Pro 6000 Blackwell's strong AI/ML compute capabilities and high score in this category make it the clear winner, outscoring the GeForce RTX 5090 Laptop by 33 points.
71 | Gaming | 99 |
73 | Workstation | 100 |
60 | AI/ML | 93 |
50 | Energy Efficiency | 49 |
67 | Quick Comparison Final Score | 98 |
| GB203-400 | Graphics Processor | GB202-300-A1 |
| 10496 | Cores | 24064 |
| 328 / 112 | TMUs / ROPs | 752 / 190 |
| 8001.96 | Blender GPU | 16644.8 |
| 154 | Forza Horizon 5 | 230 |
| 198 | The Witcher 3 | 304 |
| 213 | Counter-Strike 2 | 259 |
| 155 | Far Cry 6 | 198 |
| 123 | Hogwarts Legacy | 192 |
| 187 | Call of Duty | 301 |
| 115 | Ghost of Tsushima | 172 |
| 155 | Cyberpunk 2077 | 221 |
| 260 | Tomb Raider | 303 |
| 173 | Average FPS | 242 |
| 202 | 1080p High | 282 |
| 173 | 1080p Ultra | 242 |
| 137 | 1440p Ultra | 197 |
| 80 | 4K Ultra | 118 |
| Low | Margin of Error | High |
| 226752 | GB6 Compute Score | 419470 |
| 266.5 img/sec | Background Blur | 366.1 img/sec |
| 196.9 img/sec | Face Detection | 248 img/sec |
| 10.6 Gpixels/sec | Horizon Detection | 23.3 Gpixels/sec |
| 15.2 Gpixels/sec | Edge Detection | 35.2 Gpixels/sec |
| 14.4 Gpixels/sec | Gaussian Blur | 45 Gpixels/sec |
| 1.89 Gpixels/sec | Feature Matching | 2.47 Gpixels/sec |
| 1150 Gpixels/sec | Stereo Matching | 3040 Gpixels/sec |
| 29783 FPS | Particle Physics | 42574.6 FPS |
| OpenCL | API | OpenCL |
| 28298 | G3D Mark Score | 37305 |
| 1094 | G2D Mark | 1375 |
| 265 FPS | DirectX 11 | 338 FPS |
| 136 FPS | DirectX 12 | 153 FPS |
| 11559 Ops/s | GPU Compute | 26895 Ops/s |
| 30250 | GB6 ML Single Precision | 50053 |
| 52126 | GB6 ML Half Precision | 74036 |
| 23496 | GB6 ML Quantized | 37636 |
| 12121 | Image Classification (SP) | 16903 |
| 33054 | Image Segmentation (HP) | 48518 |
| 33652 | Image Super Resolution (Q) | 54618 |
| 67213 | Face Detection (HP) | 103224 |
| 151395 | Pose Estimation (Q) | 338587 |
| 3209 | Text Classification (SP) | 3894 |
| 6292 | Machine Translation (HP) | 7291 |
| 15618 | Object Detection (SP) | 26498 |
| 57894 | Depth Estimation (Q) | 90853 |
| 272117 | Style Transfer (SP) | 635289 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 170-242 GPixel/s | Pixel Fill Rate | 497 GPixel/s |
| 497-708 GTexel/s | Texture Fill Rate | 1968 GTexel/s |
| 31.8-45.3 TFLOPS | FLOPS (FP32) | 126 TFLOPS |
| GDDR7 | Memory Type | GDDR7 |
| 24 GB | Memory Size | 96 GB |
| 1750 MHz | Memory Clock | 1750 MHz |
| 28000 Mbps | Effective Memory Speed | 28000 Mbps |
| 256-bit | Bus | 512-bit |
| No | ECC | Yes |
| 896 GB/s | Memory Bandwidth | 1792 GB/s |
| PCIe 5.0 x16 | Interface | PCIe 5.0 x16 |
| 95-175 W (configurable) | TGP | 600 W |
| TSMC | Manufacturing | TSMC |
| 4 nm | Fabrication Process | 5 nm |
| 378 mm² | Die Size | 750 mm² |
| 45.6 billion | Transistor Count | 92.2 billion |
| 120.63 MTr/mm² | Transistor Density | 122.93 MTr/mm² |
| 12 | DirectX | 12.2 |
| 1.4 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 10.1 | CUDA | 12 |
| Yes | Ray Tracing | Yes |
| DLSS 4 | DLSS | DLSS 4 |
| 2.1a | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 6, 2025 | Released | March 18, 2026 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Professional |
| High-end | Segment | High-end |
| Blackwell 2.0 | Architecture | Blackwell 2.0 |
| GB203-400 | GPU Codename | GB202-300-A1 |
| -Intel Core Ultra 9 275HXor above | Recommended CPU | -AMD Ryzen 9 9955HX3Dor above |
| 26140 | Steel Nomad Lite Score | 50516 |
| 25013 | Time Spy | 42437 |
| 115677 | Solar Bay | 258808 |
| 16533 | Port Royal | 39952 |
| 51096 | Fire Strike | 72183 |
| 47099 | Wild Life Extreme | 110070 |
| 177139 | Night Raid | 216213 |
| 990-1515 MHz (configurable) | Base Clock | 1590 MHz |
| 1515-2160 MHz (configurable) | Boost Clock | 2617 MHz |
| 10496 | Shading Units | 24064 |
| 328 | Texture Mapping Units (TMUs) | 752 |
| 112 | Render Output Units (ROPs) | 190 |
| 82 | Compute Units (Pipelines) | 188 |
| 328 | Tensor Cores | 752 |
| 82 | 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 |
Compare with something else?
Compare GeForce RTX 5090 with another →