Quick/Comparisons
A budget Nvidia GeForce GTX 1070 Ti graphics card with limited performance overall, higher power consumption. Suited for casual gaming and basic graphics tasks.
| Gaming | 22 /100 |
| Workstation | 28 /100 |
| AI/ML | 16 /100 |
| Energy Efficiency | 20 |
Looking for more comparisons?
Compare GeForce GTX →| Quick Comparison Final Score | 23 /100 |
| Graphics Processor | GP104 |
| Cores | 2432 |
| TMUs / ROPs | 152 / 64 |
| Blender GPU | 629.59 |
| Forza Horizon 5 | 55 |
| The Witcher 3 | 77 |
| Counter-Strike 2 | 108 |
| Far Cry 6 | 70 |
| Hogwarts Legacy | 42 |
| Call of Duty | 53 |
| Ghost of Tsushima | 39 |
| Cyberpunk 2077 | 45 |
| Tomb Raider | 80 |
| Average FPS | 63 |
| 1080p High | 79 |
| 1080p Ultra | 63 |
| 1440p Ultra | 45 |
| 4K Ultra | 24 |
| Margin of Error | Low |
| GB6 Compute Score | 57735 |
| Background Blur | 149.2 img/sec |
| Face Detection | 67.6 img/sec |
| Horizon Detection | 2.36 Gpixels/sec |
| Edge Detection | 3.57 Gpixels/sec |
| Gaussian Blur | 4.32 Gpixels/sec |
| Feature Matching | 0.27 Gpixels/sec |
| Stereo Matching | 209.6 Gpixels/sec |
| Particle Physics | 6584.9 FPS |
| API | OpenCL |
| G3D Mark Score | 14658 |
| G2D Mark | 876 |
| DirectX 11 | 107 FPS |
| DirectX 12 | 52 FPS |
| GPU Compute | 7162 Ops/s |
| GB6 ML Single Precision | 8949 |
| GB6 ML Half Precision | 8769 |
| GB6 ML Quantized | 6546 |
| Image Classification (SP) | 3473 |
| Image Segmentation (HP) | 5149 |
| Image Super Resolution (Q) | 9722 |
| Face Detection (HP) | 9306 |
| Pose Estimation (Q) | 34870 |
| Text Classification (SP) | 2139 |
| Machine Translation (HP) | 2424 |
| Object Detection (SP) | 4566 |
| Depth Estimation (Q) | 14316 |
| Style Transfer (SP) | 88984 |
| Framework | ONNX |
| Backend | DirectML |
| Pixel Fill Rate | 108 GPixel/s |
| Texture Fill Rate | 256 GTexel/s |
| FLOPS (FP32) | 8.2 TFLOPS |
| Memory Type | GDDR5 |
| Memory Size | 8 GB |
| Memory Clock | 2002 MHz |
| Effective Memory Speed | 8000 Mbps |
| Bus | 256-bit |
| ECC | No |
| Memory Bandwidth | 256.3 GB/s |
| Interface | PCIe 3.0 x16 |
| TGP | 180 W |
| Manufacturing | TSMC |
| Fabrication Process | 16 nm |
| Die Size | 314 mm² |
| Transistor Count | 7 billion |
| Transistor Density | 22.29 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 | November 2, 2017 |
| Case | Desktop |
| Purpose | Gaming |
| Segment | Mid-range |
| Architecture | Pascal |
| GPU Codename | GP104 |
| Recommended CPU | -Intel Core i7 7700Kor above |
| Steel Nomad Lite Score | 6671 |
| Time Spy | 6843 |
| Solar Bay | 18267 |
| Port Royal | 1552 |
| Fire Strike | 20115 |
| Wild Life Extreme | 13248 |
| Night Raid | 78890 |
| Base Clock | 1607 MHz |
| Boost Clock | 1683 MHz |
| Shading Units | 2432 |
| Texture Mapping Units (TMUs) | 152 |
| Render Output Units (ROPs) | 64 |
| Compute Units (Pipelines) | 19 |
| Tensor Cores | No |
| Ray-tracing Cores | No |
| L1 Cache | 48KB per cluster |
| L2 Cache | 2MB shared |
| Instructions Per Cycle | 2 IPC |
84/100