Quick/Comparisons
The Nvidia RTX Pro 6000 Blackwell's exceptional gaming performance, with a score of 99, far surpasses the GeForce GTX 1660's score of 18.
The Nvidia RTX Pro 6000 Blackwell's perfect score of 100 in workstation performance makes it the clear winner in content creation tasks.
Although the GeForce GTX 1660 has dedicated AI tensor cores, the Nvidia RTX Pro 6000 Blackwell's score of 93 in AI/ML compute is significantly higher than the GeForce GTX 1660's score of 15.
18 | Gaming | 99 |
26 | Workstation | 100 |
15 | AI/ML | 93 |
44 | Energy Efficiency | 49 |
21 | Quick Comparison Final Score | 98 |
| TU116 | Graphics Processor | GB202-300-A1 |
| 1408 | Cores | 24064 |
| 88 / 48 | TMUs / ROPs | 752 / 190 |
| 721.98 | Blender GPU | 16644.8 |
| 46 | Forza Horizon 5 | 230 |
| 58 | The Witcher 3 | 304 |
| 83 | Counter-Strike 2 | 259 |
| 56 | Far Cry 6 | 198 |
| 34 | Hogwarts Legacy | 192 |
| 39 | Call of Duty | 301 |
| 28 | Ghost of Tsushima | 172 |
| 39 | Cyberpunk 2077 | 221 |
| 65 | Tomb Raider | 303 |
| 50 | Average FPS | 242 |
| 63 | 1080p High | 282 |
| 50 | 1080p Ultra | 242 |
| 35 | 1440p Ultra | 197 |
| 18 | 4K Ultra | 118 |
| Low | Margin of Error | High |
| 60105 | GB6 Compute Score | 419470 |
| 107.7 img/sec | Background Blur | 366.1 img/sec |
| 58.6 img/sec | Face Detection | 248 img/sec |
| 2.07 Gpixels/sec | Horizon Detection | 23.3 Gpixels/sec |
| 2.61 Gpixels/sec | Edge Detection | 35.2 Gpixels/sec |
| 3 Gpixels/sec | Gaussian Blur | 45 Gpixels/sec |
| 0.77 Gpixels/sec | Feature Matching | 2.47 Gpixels/sec |
| 301.7 Gpixels/sec | Stereo Matching | 3040 Gpixels/sec |
| 8078.5 FPS | Particle Physics | 42574.6 FPS |
| OpenCL | API | OpenCL |
| 11620 | G3D Mark Score | 37305 |
| 776 | G2D Mark | 1375 |
| 79 FPS | DirectX 11 | 338 FPS |
| 49 FPS | DirectX 12 | 153 FPS |
| 4938 Ops/s | GPU Compute | 26895 Ops/s |
| 8617 | GB6 ML Single Precision | 50053 |
| 7365 | GB6 ML Half Precision | 74036 |
| 6243 | GB6 ML Quantized | 37636 |
| 3814 | Image Classification (SP) | 16903 |
| 4931 | Image Segmentation (HP) | 48518 |
| 8081 | Image Super Resolution (Q) | 54618 |
| 8691 | Face Detection (HP) | 103224 |
| 33497 | Pose Estimation (Q) | 338587 |
| 1586 | Text Classification (SP) | 3894 |
| 2227 | Machine Translation (HP) | 7291 |
| 4384 | Object Detection (SP) | 26498 |
| 16173 | Depth Estimation (Q) | 90853 |
| 72011 | Style Transfer (SP) | 635289 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 86 GPixel/s | Pixel Fill Rate | 497 GPixel/s |
| 157 GTexel/s | Texture Fill Rate | 1968 GTexel/s |
| 5 TFLOPS | FLOPS (FP32) | 126 TFLOPS |
| GDDR5 | Memory Type | GDDR7 |
| 6 GB | Memory Size | 96 GB |
| 2001 MHz | Memory Clock | 1750 MHz |
| 8000 Mbps | Effective Memory Speed | 28000 Mbps |
| 192-bit | Bus | 512-bit |
| No | ECC | Yes |
| 192.1 GB/s | Memory Bandwidth | 1792 GB/s |
| PCIe 3.0 x16 | Interface | PCIe 5.0 x16 |
| 120 W | TGP | 600 W |
| TSMC | Manufacturing | TSMC |
| 12 nm | Fabrication Process | 5 nm |
| 284 mm² | Die Size | 750 mm² |
| 6 billion | Transistor Count | 92.2 billion |
| 21.13 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 |
| 7.5 | CUDA | 12 |
| No | Ray Tracing | Yes |
| No | DLSS | DLSS 4 |
| 1.4a | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| March 14, 2019 | Released | March 18, 2026 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Professional |
| Entry-level | Segment | High-end |
| Turing | Architecture | Blackwell 2.0 |
| TU116 | GPU Codename | GB202-300-A1 |
| -Intel Core i5 9500or above | Recommended CPU | -AMD Ryzen 9 9955HX3Dor above |
| 5101 | Steel Nomad Lite Score | 50516 |
| 5443 | Time Spy | 42437 |
| 18093 | Solar Bay | 258808 |
| 1455 | Port Royal | 39952 |
| 14206 | Fire Strike | 72183 |
| 10949 | Wild Life Extreme | 110070 |
| 66346 | Night Raid | 216213 |
| 1530 MHz | Base Clock | 1590 MHz |
| 1785 MHz | Boost Clock | 2617 MHz |
| 1408 | Shading Units | 24064 |
| 88 | Texture Mapping Units (TMUs) | 752 |
| 48 | Render Output Units (ROPs) | 190 |
| 22 | Compute Units (Pipelines) | 188 |
| No | Tensor Cores | 752 |
| No | Ray-tracing Cores | 188 |
| 64KB per cluster | L1 Cache | 128KB per cluster |
| 1536KB shared | L2 Cache | 128MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce GTX 1660 with another →