Quick/Comparisons
A entry-level Nvidia GeForce GTX 1080 Ti graphics card with modest workstation performance (36/100), higher power consumption. Suited for casual gaming and basic graphics tasks.
| Gaming | 31 /100 |
| Workstation | 36 /100 |
| AI/ML | 23 /100 |
| Energy Efficiency | 20 |
Looking for more comparisons?
Compare GeForce GTX →| Quick Comparison Final Score | 32 /100 |
| Graphics Processor | GP102 |
| Cores | 3584 |
| TMUs / ROPs | 224 / 88 |
| Blender GPU | 860.72 |
| Forza Horizon 5 | 75 |
| The Witcher 3 | 111 |
| Counter-Strike 2 | 144 |
| Far Cry 6 | 89 |
| Hogwarts Legacy | 62 |
| Call of Duty | 80 |
| Ghost of Tsushima | 57 |
| Cyberpunk 2077 | 69 |
| Tomb Raider | 108 |
| Average FPS | 88 |
| 1080p High | 108 |
| 1080p Ultra | 88 |
| 1440p Ultra | 65 |
| 4K Ultra | 36 |
| Margin of Error | Low |
| GB6 Compute Score | 74966 |
| Background Blur | 200.9 img/sec |
| Face Detection | 88.6 img/sec |
| Horizon Detection | 3.55 Gpixels/sec |
| Edge Detection | 5.57 Gpixels/sec |
| Gaussian Blur | 5.79 Gpixels/sec |
| Feature Matching | 0.33 Gpixels/sec |
| Stereo Matching | 265.6 Gpixels/sec |
| Particle Physics | 6315.6 FPS |
| API | OpenCL |
| G3D Mark Score | 18589 |
| G2D Mark | 940 |
| DirectX 11 | 151 FPS |
| DirectX 12 | 66 FPS |
| GPU Compute | 9593 Ops/s |
| GB6 ML Single Precision | 12690 |
| GB6 ML Half Precision | 12039 |
| GB6 ML Quantized | 8644 |
| Image Classification (SP) | 3882 |
| Image Segmentation (HP) | 7960 |
| Image Super Resolution (Q) | 14401 |
| Face Detection (HP) | 13001 |
| Pose Estimation (Q) | 72329 |
| Text Classification (SP) | 1910 |
| Machine Translation (HP) | 3577 |
| Object Detection (SP) | 4757 |
| Depth Estimation (Q) | 20303 |
| Style Transfer (SP) | 164740 |
| Framework | ONNX |
| Backend | DirectML |
| Pixel Fill Rate | 139 GPixel/s |
| Texture Fill Rate | 354 GTexel/s |
| FLOPS (FP32) | 11.3 TFLOPS |
| Memory Type | GDDR5X |
| Memory Size | 11 GB |
| Memory Clock | 1376 MHz |
| Effective Memory Speed | 11000 Mbps |
| Bus | 352-bit |
| ECC | No |
| Memory Bandwidth | 484.4 GB/s |
| Interface | PCIe 3.0 x16 |
| TGP | 250 W |
| Manufacturing | TSMC |
| Fabrication Process | 16 nm |
| Die Size | 471 mm² |
| Transistor Count | 11 billion |
| Transistor Density | 23.35 MTr/mm² |
| DirectX | 12 |
| Vulkan | 1.3 |
| OpenGL | 4.6 |
| OpenCL | 3 |
| CUDA | 6.1 |
| Ray Tracing | No |
| DLSS | No |
| DisplayPort | 1.4a |
| Vendor | Nvidia |
| Build | Discrete |
| Released | March 10, 2017 |
| Case | Desktop |
| Purpose | Gaming |
| Segment | High-end |
| Architecture | Pascal |
| GPU Codename | GP102 |
| Recommended CPU | -Intel Core i7 7700Kor above |
| Steel Nomad Lite Score | 9652 |
| Time Spy | 9982 |
| Solar Bay | 26207 |
| Port Royal | 2263 |
| Fire Strike | 29329 |
| Wild Life Extreme | 20168 |
| Night Raid | 95786 |
| Base Clock | 1481 MHz |
| Boost Clock | 1582 MHz |
| Shading Units | 3584 |
| Texture Mapping Units (TMUs) | 224 |
| Render Output Units (ROPs) | 88 |
| Compute Units (Pipelines) | 28 |
| Tensor Cores | No |
| Ray-tracing Cores | No |
| L1 Cache | 48KB per cluster |
| L2 Cache | 2816KB shared |
| Instructions Per Cycle | 2 IPC |
84/100