Quick/Comparisons
46 | Gaming | 80 |
49 | Workstation | 94 |
39 | AI/ML |
Compare with something else?
Compare GeForce RTX 3070 with another →75 |
35 | Energy Efficiency | 44 |
46 | Quick Comparison Final Score | 83 |
| GA104 | Graphics Processor | AD102 |
| 6144 | Cores | 18176 |
| 192 / 96 | TMUs / ROPs | 568 / 192 |
| 3746.83 | Blender GPU | 11038.91 |
| 104 | Forza Horizon 5 | 165 |
| 143 | The Witcher 3 | 219 |
| 198 | Counter-Strike 2 | 221 |
| 125 | Far Cry 6 | 164 |
| 85 | Hogwarts Legacy | 133 |
| 120 | Call of Duty | 216 |
| 81 | Ghost of Tsushima | 123 |
| 102 | Cyberpunk 2077 | 172 |
| 161 | Tomb Raider | 267 |
| 124 | Average FPS | 187 |
| 150 | 1080p High | 219 |
| 124 | 1080p Ultra | 187 |
| 93 | 1440p Ultra | 148 |
| 54 | 4K Ultra | 89 |
| Low | Margin of Error | High |
| 136096 | GB6 Compute Score | 389848 |
| 197 img/sec | Background Blur | 618.3 img/sec |
| 128.1 img/sec | Face Detection | 399.9 img/sec |
| 6.56 Gpixels/sec | Horizon Detection | 15.1 Gpixels/sec |
| 8.81 Gpixels/sec | Edge Detection | 22.1 Gpixels/sec |
| 6.47 Gpixels/sec | Gaussian Blur | 26.3 Gpixels/sec |
| 1.26 Gpixels/sec | Feature Matching | 2.33 Gpixels/sec |
| 609.3 Gpixels/sec | Stereo Matching | 2210 Gpixels/sec |
| 18205 FPS | Particle Physics | 53494.5 FPS |
| OpenCL | API | OpenCL |
| 23260 | G3D Mark Score | 28613 |
| 1061 | G2D Mark | 1005 |
| 192 FPS | DirectX 11 | 284 FPS |
| 91 FPS | DirectX 12 | 102 FPS |
| 11452 Ops/s | GPU Compute | 22439 Ops/s |
| 22516 | GB6 ML Single Precision | 37270 |
| 36377 | GB6 ML Half Precision | 53469 |
| 14215 | GB6 ML Quantized | 27850 |
| 8615 | Image Classification (SP) | 13367 |
| 24659 | Image Segmentation (HP) | 32477 |
| 20631 | Image Super Resolution (Q) | 42056 |
| 43834 | Face Detection (HP) | 69004 |
| 98347 | Pose Estimation (Q) | 230965 |
| 3162 | Text Classification (SP) | 3491 |
| 4911 | Machine Translation (HP) | 5545 |
| 11498 | Object Detection (SP) | 18668 |
| 34719 | Depth Estimation (Q) | 68370 |
| 196833 | Style Transfer (SP) | 520389 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 170 GPixel/s | Pixel Fill Rate | 481 GPixel/s |
| 340 GTexel/s | Texture Fill Rate | 1423 GTexel/s |
| 21.7 TFLOPS | FLOPS (FP32) | 91.1 TFLOPS |
| GDDR6X | Memory Type | GDDR6 |
| 8 GB | Memory Size | 48 GB |
| 1188 MHz | Memory Clock | 2500 MHz |
| 19000 Mbps | Effective Memory Speed | 20000 Mbps |
| 256-bit | Bus | 384-bit |
| No | ECC | No |
| 608.3 GB/s | Memory Bandwidth | 960 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 290 W | TGP | 300 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 5 nm |
| 392 mm² | Die Size | 609 mm² |
| 17 billion | Transistor Count | 76 billion |
| 43.37 MTr/mm² | Transistor Density | 124.79 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.6 | CUDA | 8.9 |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | DLSS 3 |
| 1.4a | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| June 10, 2021 | Released | December 3, 2022 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Professional |
| Mid-range | Segment | High-end |
| Ampere | Architecture | Ada Lovelace |
| GA104 | GPU Codename | AD102 |
| -Intel Core i7 12700Kor above | Recommended CPU | -Intel Core i9 14900Kor above |
| 15402 | Steel Nomad Lite Score | 32284 |
| 14880 | Time Spy | 26686 |
| 69900 | Solar Bay | 145429 |
| 8884 | Port Royal | 19557 |
| 37238 | Fire Strike | 62803 |
| 31911 | Wild Life Extreme | 53640 |
| 134012 | Night Raid | 148225 |
| 1575 MHz | Base Clock | 915 MHz |
| 1770 MHz | Boost Clock | 2505 MHz |
| 6144 | Shading Units | 18176 |
| 192 | Texture Mapping Units (TMUs) | 568 |
| 96 | Render Output Units (ROPs) | 192 |
| 48 | Compute Units (Pipelines) | 142 |
| 192 | Tensor Cores | 568 |
| 48 | Ray-tracing Cores | 142 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 4MB shared | L2 Cache | 96MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |