Quick/Comparisons
34 | Gaming | 12 |
41 | Workstation | 17 |
31 | AI/ML |
Compare with something else?
Compare GeForce RTX 3070 with another →18 |
43 | Energy Efficiency | 85 |
37 | Quick Comparison Final Score | 26 |
| GA104 (GN20-E5) | Graphics Processor | Strix Point |
| 5120 | Cores | 1024 |
| 160 / 80 | TMUs / ROPs | 64 / 32 |
| 2998.92 | Blender GPU | 311.81 |
| 79 | Forza Horizon 5 | 28 |
| 114 | The Witcher 3 | 28 |
| 150 | Counter-Strike 2 | 32 |
| 94 | Far Cry 6 | 38 |
| 61 | Hogwarts Legacy | 19 |
| 88 | Call of Duty | 32 |
| 56 | Ghost of Tsushima | 16 |
| 73 | Cyberpunk 2077 | 22 |
| 116 | Tomb Raider | 35 |
| 92 | Average FPS | 28 |
| 114 | 1080p High | 38 |
| 92 | 1080p Ultra | 28 |
| 68 | 1440p Ultra | 19 |
| 38 | 4K Ultra | 10 |
| Low | Margin of Error | Low |
| 118499 | GB6 Compute Score | 42932 |
| 170.3 img/sec | Background Blur | 98.6 img/sec |
| 113.6 img/sec | Face Detection | 42 img/sec |
| 5.59 Gpixels/sec | Horizon Detection | 1.25 Gpixels/sec |
| 7.94 Gpixels/sec | Edge Detection | 1.6 Gpixels/sec |
| 6.19 Gpixels/sec | Gaussian Blur | 1.69 Gpixels/sec |
| 1.16 Gpixels/sec | Feature Matching | 0.55 Gpixels/sec |
| 467 Gpixels/sec | Stereo Matching | 214.8 Gpixels/sec |
| 15131.3 FPS | Particle Physics | 7757.7 FPS |
| OpenCL | API | OpenCL |
| 15105 | G3D Mark Score | 8122 |
| 630 | G2D Mark | 976 |
| 137 FPS | DirectX 11 | 73 FPS |
| 63 FPS | DirectX 12 | 37 FPS |
| 6702 Ops/s | GPU Compute | 4164 Ops/s |
| 17250 | GB6 ML Single Precision | 9613 |
| 27936 | GB6 ML Half Precision | 15157 |
| 11249 | GB6 ML Quantized | 7082 |
| 6969 | Image Classification (SP) | 3563 |
| 17142 | Image Segmentation (HP) | 6170 |
| 16426 | Image Super Resolution (Q) | 10762 |
| 31628 | Face Detection (HP) | 13773 |
| 74413 | Pose Estimation (Q) | 37861 |
| 2522 | Text Classification (SP) | 2572 |
| 3639 | Machine Translation (HP) | 4699 |
| 9002 | Object Detection (SP) | 2845 |
| 27790 | Depth Estimation (Q) | 17260 |
| 160005 | Style Transfer (SP) | 86751 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 103-130 GPixel/s | Pixel Fill Rate | 93 GPixel/s |
| 206-259 GTexel/s | Texture Fill Rate | 186 GTexel/s |
| 13.2-16.6 TFLOPS | FLOPS (FP32) | 5.9 TFLOPS |
| GDDR6 | Memory Type | System Shared |
| 8 GB | Memory Size | — |
| 1500-1750 MHz | Memory Clock | — |
| 12000-14000 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 | 233 mm² |
| 17.4 billion | Transistor Count | 34 billion |
| 44.39 MTr/mm² | Transistor Density | 145.92 MTr/mm² |
| 12 | DirectX | 12 |
| 1.2 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 2 | OpenCL | 2.1 |
| 8.6 | CUDA | None |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| January 12, 2021 | Released | June 3, 2024 |
| Laptop | Case | Laptop |
| Gaming | Purpose | Generic |
| High-end | Segment | Mid-range |
| Ampere | Architecture | RDNA 3.5 |
| GA104 (GN20-E5) | GPU Codename | Strix Point |
| -Intel Core i7 12700Hor above | Recommended CPU | -AMD Ryzen AI 9 HX 370or above |
| 10214 | Steel Nomad Lite Score | 3190 |
| 10477 | Time Spy | 3307 |
| 45215 | Solar Bay | 15184 |
| 6247 | Port Royal | 1790 |
| 26729 | Fire Strike | 8885 |
| 21137 | Wild Life Extreme | 6775 |
| 82533 | Night Raid | 37532 |
| 780-1215 MHz (configurable) | Base Clock | 400 MHz |
| 1290-1620 MHz (configurable) | Boost Clock | 2900 MHz |
| 5120 | Shading Units | 1024 |
| 160 | Texture Mapping Units (TMUs) | 64 |
| 80 | Render Output Units (ROPs) | 32 |
| 40 | Compute Units (Pipelines) | 16 |
| 160 | Tensor Cores | No |
| 40 | Ray-tracing Cores | 16 |
| 128KB per cluster | L1 Cache | 512KB per cluster |
| 4MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |