Quick/Comparisons
43 | Gaming | 39 |
44 | Workstation | 41 |
35 | AI/ML |
Compare with something else?
Compare GeForce RTX 3070 with another →34 |
35 | Energy Efficiency | 68 |
42 | Quick Comparison Final Score | 44 |
| GA104 | Graphics Processor | GB206 |
| 5888 | Cores | 3328 |
| 184 / 96 | TMUs / ROPs | 104 / 48 |
| 3368.42 | Blender GPU | 3486.18 |
| 99 | Forza Horizon 5 | 88 |
| 143 | The Witcher 3 | 124 |
| 194 | Counter-Strike 2 | 169 |
| 121 | Far Cry 6 | 104 |
| 80 | Hogwarts Legacy | 73 |
| 113 | Call of Duty | 102 |
| 74 | Ghost of Tsushima | 66 |
| 94 | Cyberpunk 2077 | 83 |
| 153 | Tomb Raider | 131 |
| 119 | Average FPS | 104 |
| 141 | 1080p High | 127 |
| 119 | 1080p Ultra | 104 |
| 88 | 1440p Ultra | 77 |
| 50 | 4K Ultra | 44 |
| Low | Margin of Error | Low |
| 126195 | GB6 Compute Score | 116707 |
| 161.6 img/sec | Background Blur | 190.8 img/sec |
| 117.2 img/sec | Face Detection | 115.9 img/sec |
| 5.89 Gpixels/sec | Horizon Detection | 4.17 Gpixels/sec |
| 8.05 Gpixels/sec | Edge Detection | 5.28 Gpixels/sec |
| 6.65 Gpixels/sec | Gaussian Blur | 7.1 Gpixels/sec |
| 1.25 Gpixels/sec | Feature Matching | 1.32 Gpixels/sec |
| 550.6 Gpixels/sec | Stereo Matching | 523.3 Gpixels/sec |
| 17613.1 FPS | Particle Physics | 16169.3 FPS |
| OpenCL | API | OpenCL |
| 22128 | G3D Mark Score | 16865 |
| 1005 | G2D Mark | 854 |
| 182 FPS | DirectX 11 | 163 FPS |
| 84 FPS | DirectX 12 | 79 FPS |
| 11062 Ops/s | GPU Compute | 6246 Ops/s |
| 19789 | GB6 ML Single Precision | 18679 |
| 33013 | GB6 ML Half Precision | 35323 |
| 12443 | GB6 ML Quantized | 14707 |
| 7624 | Image Classification (SP) | 7525 |
| 23420 | Image Segmentation (HP) | 23623 |
| 17898 | Image Super Resolution (Q) | 19973 |
| 40535 | Face Detection (HP) | 41164 |
| 83624 | Pose Estimation (Q) | 77589 |
| 2724 | Text Classification (SP) | 2880 |
| 4481 | Machine Translation (HP) | 5811 |
| 10304 | Object Detection (SP) | 9966 |
| 30418 | Depth Estimation (Q) | 37206 |
| 180089 | Style Transfer (SP) | 136961 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 166 GPixel/s | Pixel Fill Rate | 70-120 GPixel/s |
| 317 GTexel/s | Texture Fill Rate | 151-260 GTexel/s |
| 20.3 TFLOPS | FLOPS (FP32) | 9.7-16.6 TFLOPS |
| GDDR6 | Memory Type | GDDR7 |
| 8 GB | Memory Size | 8 GB |
| 1750 MHz | Memory Clock | 1750 MHz |
| 14000 Mbps | Effective Memory Speed | 24000 Mbps |
| 256-bit | Bus | 128-bit |
| No | ECC | No |
| 448 GB/s | Memory Bandwidth | 384 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 5.0 x16 |
| 220 W | TGP | 45-115 W (configurable) |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 4 nm |
| 392 mm² | Die Size | 181 mm² |
| 17 billion | Transistor Count | 21.9 billion |
| 43.37 MTr/mm² | Transistor Density | 120.99 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 |
| DLSS 2 | DLSS | DLSS 4 |
| 1.4a | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| October 22, 2020 | Released | April 14, 2025 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | Mid-range |
| Ampere | Architecture | Blackwell 2.0 |
| GA104 | GPU Codename | GB206 |
| -Intel Core i7 12700Kor above | Recommended CPU | -Intel Core Ultra 5 245HXor above |
| 14153 | Steel Nomad Lite Score | 11858 |
| 13643 | Time Spy | 12013 |
| 64426 | Solar Bay | 52525 |
| 8311 | Port Royal | 7419 |
| 34054 | Fire Strike | 31691 |
| 28486 | Wild Life Extreme | 21567 |
| 122039 | Night Raid | 116013 |
| 1500 MHz | Base Clock | 952-1455 MHz (configurable) |
| 1725 MHz | Boost Clock | 1455-2497 MHz (configurable) |
| 5888 | Shading Units | 3328 |
| 184 | Texture Mapping Units (TMUs) | 104 |
| 96 | Render Output Units (ROPs) | 48 |
| 46 | Compute Units (Pipelines) | 26 |
| 184 | Tensor Cores | 104 |
| 46 | Ray-tracing Cores | 26 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 4MB shared | L2 Cache | 32MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |