Quick/Comparisons
The Nvidia RTX Pro 6000 Blackwell's exceptional gaming performance and high score of 99 make it the clear winner. Its capabilities far surpass the GeForce RTX 2050 Mobile's score of 14.
The Nvidia RTX Pro 6000 Blackwell's perfect score of 100 in workstation performance makes it the clear winner, outperforming the GeForce RTX 2050 Mobile's score of 20.
The Nvidia RTX Pro 6000 Blackwell's strong AI/ML compute capabilities and high score of 93 make it the winner, although the GeForce RTX 2050 Mobile's score of 14 is not far behind.
14 | Gaming | 99 |
20 | Workstation | 100 |
14 | AI/ML | 93 |
75 | Energy Efficiency | 49 |
26 | Quick Comparison Final Score | 98 |
| GA107 | Graphics Processor | GB202-300-A1 |
| 2048 | Cores | 24064 |
| 64 / 32 | TMUs / ROPs | 752 / 190 |
| 749.91 | Blender GPU | 16644.8 |
| 35 | Forza Horizon 5 | 230 |
| 41 | The Witcher 3 | 304 |
| 60 | Counter-Strike 2 | 259 |
| 44 | Far Cry 6 | 198 |
| 23 | Hogwarts Legacy | 192 |
| 32 | Call of Duty | 301 |
| 21 | Ghost of Tsushima | 172 |
| 26 | Cyberpunk 2077 | 221 |
| 50 | Tomb Raider | 303 |
| 37 | Average FPS | 242 |
| 47 | 1080p High | 282 |
| 37 | 1080p Ultra | 242 |
| 25 | 1440p Ultra | 197 |
| 13 | 4K Ultra | 118 |
| Low | Margin of Error | High |
| 42967 | GB6 Compute Score | 419470 |
| 73.3 img/sec | Background Blur | 366.1 img/sec |
| 39.7 img/sec | Face Detection | 248 img/sec |
| 1.65 Gpixels/sec | Horizon Detection | 23.3 Gpixels/sec |
| 2.13 Gpixels/sec | Edge Detection | 35.2 Gpixels/sec |
| 2.06 Gpixels/sec | Gaussian Blur | 45 Gpixels/sec |
| 0.55 Gpixels/sec | Feature Matching | 2.47 Gpixels/sec |
| 191.1 Gpixels/sec | Stereo Matching | 3040 Gpixels/sec |
| 5921.5 FPS | Particle Physics | 42574.6 FPS |
| OpenCL | API | OpenCL |
| 7710 | G3D Mark Score | 37305 |
| 480 | G2D Mark | 1375 |
| 47 FPS | DirectX 11 | 338 FPS |
| 42 FPS | DirectX 12 | 153 FPS |
| 3502 Ops/s | GPU Compute | 26895 Ops/s |
| 7807 | GB6 ML Single Precision | 50053 |
| 14632 | GB6 ML Half Precision | 74036 |
| 5491 | GB6 ML Quantized | 37636 |
| 3489 | Image Classification (SP) | 16903 |
| 7528 | Image Segmentation (HP) | 48518 |
| 6509 | Image Super Resolution (Q) | 54618 |
| 13217 | Face Detection (HP) | 103224 |
| 24531 | Pose Estimation (Q) | 338587 |
| 2148 | Text Classification (SP) | 3894 |
| 2764 | Machine Translation (HP) | 7291 |
| 3948 | Object Detection (SP) | 26498 |
| 13355 | Depth Estimation (Q) | 90853 |
| 60626 | Style Transfer (SP) | 635289 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 40-47 GPixel/s | Pixel Fill Rate | 497 GPixel/s |
| 80-95 GTexel/s | Texture Fill Rate | 1968 GTexel/s |
| 5.1-6 TFLOPS | FLOPS (FP32) | 126 TFLOPS |
| GDDR6 | Memory Type | GDDR7 |
| 4 GB | Memory Size | 96 GB |
| 1750 MHz | Memory Clock | 1750 MHz |
| 14000 Mbps | Effective Memory Speed | 28000 Mbps |
| 64-bit | Bus | 512-bit |
| No | ECC | Yes |
| 112 GB/s | Memory Bandwidth | 1792 GB/s |
| PCIe 3.0 x8 | Interface | PCIe 5.0 x16 |
| 30-45 W (configurable) | TGP | 600 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 5 nm |
| 200 mm² | Die Size | 750 mm² |
| 8 billion | Transistor Count | 92.2 billion |
| 40 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 |
| No | DLSS | DLSS 4 |
| 1.4a | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| December 17, 2021 | Released | March 18, 2026 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Professional |
| Mid-range | Segment | High-end |
| Ampere | Architecture | Blackwell 2.0 |
| GA107 | GPU Codename | GB202-300-A1 |
| -Intel Core i5 11500Hor above | Recommended CPU | -AMD Ryzen 9 9955HX3Dor above |
| 3959 | Steel Nomad Lite Score | 50516 |
| 3924 | Time Spy | 42437 |
| 18938 | Solar Bay | 258808 |
| 446 | Port Royal | 39952 |
| 10490 | Fire Strike | 72183 |
| 7298 | Wild Life Extreme | 110070 |
| 45541 | Night Raid | 216213 |
| 735-1185 MHz (configurable) | Base Clock | 1590 MHz |
| 1245-1477 MHz (configurable) | Boost Clock | 2617 MHz |
| 2048 | Shading Units | 24064 |
| 64 | Texture Mapping Units (TMUs) | 752 |
| 32 | Render Output Units (ROPs) | 190 |
| 16 | Compute Units (Pipelines) | 188 |
| 64 | Tensor Cores | 752 |
| 16 | Ray-tracing Cores | 188 |
| 64KB per cluster | L1 Cache | 128KB per cluster |
| 2MB shared | L2 Cache | 128MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 2050 with another →