Quick/Comparisons
37 | Gaming | 6 |
41 | Workstation | 9 |
31 | AI/ML |
Compare with something else?
Compare GeForce RTX 3070 with another →9 |
47 | Energy Efficiency | 86 |
39 | Quick Comparison Final Score | 20 |
| GA104 (GN20-E6) | Graphics Processor | Krackan Point |
| 5632 | Cores | 256 |
| 176 / 80 | TMUs / ROPs | 16 / 8 |
| 3120.06 | Blender GPU | 122.02 |
| 85 | Forza Horizon 5 | 13 |
| 123 | The Witcher 3 | 12 |
| 167 | Counter-Strike 2 | 18 |
| 101 | Far Cry 6 | 16 |
| 67 | Hogwarts Legacy | - |
| 96 | Call of Duty | 19 |
| 63 | Ghost of Tsushima | 9 |
| 81 | Cyberpunk 2077 | 9 |
| 126 | Tomb Raider | 17 |
| 101 | Average FPS | 13 |
| 122 | 1080p High | 18 |
| 101 | 1080p Ultra | 13 |
| 74 | 1440p Ultra | 10 |
| 42 | 4K Ultra | - |
| Low | Margin of Error | High |
| 116337 | GB6 Compute Score | 14025 |
| 173.8 img/sec | Background Blur | 31.8 img/sec |
| 96.9 img/sec | Face Detection | 16.8 img/sec |
| 5.69 Gpixels/sec | Horizon Detection | 0.46 Gpixels/sec |
| 7.75 Gpixels/sec | Edge Detection | 0.58 Gpixels/sec |
| 6.27 Gpixels/sec | Gaussian Blur | 0.42 Gpixels/sec |
| 1.14 Gpixels/sec | Feature Matching | 0.18 Gpixels/sec |
| 480.4 Gpixels/sec | Stereo Matching | 52.5 Gpixels/sec |
| 14706.2 FPS | Particle Physics | 2048.6 FPS |
| OpenCL | API | OpenCL |
| 17472 | G3D Mark Score | — |
| 773 | G2D Mark | — |
| 152 FPS | DirectX 11 | — |
| 72 FPS | DirectX 12 | — |
| 7362 Ops/s | GPU Compute | — |
| 17250 | GB6 ML Single Precision | 4884 |
| 27936 | GB6 ML Half Precision | 6067 |
| 11249 | GB6 ML Quantized | 3946 |
| 6969 | Image Classification (SP) | 1988 |
| 17142 | Image Segmentation (HP) | 2184 |
| 16426 | Image Super Resolution (Q) | 4788 |
| 31628 | Face Detection (HP) | 6857 |
| 74413 | Pose Estimation (Q) | 17396 |
| 2522 | Text Classification (SP) | 1628 |
| 3639 | Machine Translation (HP) | 2053 |
| 9002 | Object Detection (SP) | 1825 |
| 27790 | Depth Estimation (Q) | 8471 |
| 160005 | Style Transfer (SP) | 31032 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 83-119 GPixel/s | Pixel Fill Rate | 23 GPixel/s |
| 182-261 GTexel/s | Texture Fill Rate | 46 GTexel/s |
| 11.7-16.7 TFLOPS | FLOPS (FP32) | 1.5 TFLOPS |
| GDDR6 | Memory Type | System Shared |
| 8 GB | Memory Size | — |
| 1750 MHz | Memory Clock | — |
| 14000 Mbps | Effective Memory Speed | — |
| 256-bit | Bus | — |
| No | ECC | — |
| 448 GB/s | Memory Bandwidth | — |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 80-150 W (configurable) | TGP | 15-54 W (configurable) |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 4 nm |
| 392 mm² | Die Size | — |
| 17.4 billion | Transistor Count | — |
| 44.39 MTr/mm² | Transistor Density | — |
| 12 | DirectX | 12 |
| 1.2 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.1 |
| 8.6 | CUDA | No |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| — | Released | January 7, 2025 |
| Laptop | Case | Laptop |
| Gaming | Purpose | Generic |
| High-end | Segment | Entry-level |
| Ampere | Architecture | RDNA 3.5 |
| GA104 (GN20-E6) | GPU Codename | Krackan Point |
| -Intel Core i7 12700Hor above | Recommended CPU | -AMD Ryzen AI 5 340or above |
| 11488 | Steel Nomad Lite Score | 1293 |
| 11331 | Time Spy | 1700 |
| 49158 | Solar Bay | 7155 |
| 6850 | Port Royal | 577 |
| 28619 | Fire Strike | 5317 |
| 23071 | Wild Life Extreme | — |
| 95266 | Night Raid | 22727 |
| 510-1035 MHz (configurable) | Base Clock | 400 MHz |
| 1035-1485 MHz (configurable) | Boost Clock | 2900 MHz |
| 5632 | Shading Units | 256 |
| 176 | Texture Mapping Units (TMUs) | 16 |
| 80 | Render Output Units (ROPs) | 8 |
| 44 | Compute Units (Pipelines) | 4 |
| 176 | Tensor Cores | No |
| 44 | Ray-tracing Cores | 4 |
| 128KB per cluster | L1 Cache | 512KB per cluster |
| 4MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |