Quick/Comparisons
The Radeon RX 7900 XTX's superior gaming performance and 81 score make it the clear winner in this use case. Its 40.5 point lead over the GeForce RTX 4070 Laptop is substantial.
The Radeon RX 7900 XTX's 35 point lead in the Content Creation use case is significant, thanks to its capable AI/ML compute and large 24GB memory pool.
The Radeon RX 7900 XTX's 36 point lead in the AI & Machine Learning use case is substantial, despite the GeForce RTX 4070 Laptop's dedicated AI tensor cores.
41 | Gaming | 81 |
40 | Workstation | 75 |
38 | AI/ML | 74 |
56 | Energy Efficiency | 43 |
43 | Quick Comparison Final Score | 77 |
| AD106 (GN21-X6) | Graphics Processor | Navi 31 |
| 4608 | Cores | 6144 |
| 144 / 48 | TMUs / ROPs | 384 / 192 |
| 3587.08 | Blender GPU | 4055.35 |
| 90 | Forza Horizon 5 | 174 |
| 132 | The Witcher 3 | 256 |
| 178 | Counter-Strike 2 | 232 |
| 112 | Far Cry 6 | 182 |
| 75 | Hogwarts Legacy | 137 |
| 104 | Call of Duty | 255 |
| 68 | Ghost of Tsushima | 138 |
| 87 | Cyberpunk 2077 | 181 |
| 139 | Tomb Raider | 277 |
| 109 | Average FPS | 204 |
| 131 | 1080p High | 241 |
| 109 | 1080p Ultra | 204 |
| 81 | 1440p Ultra | 159 |
| 46 | 4K Ultra | 94 |
| Low | Margin of Error | Low |
| 115081 | GB6 Compute Score | 224686 |
| 158.5 img/sec | Background Blur | 423.9 img/sec |
| 116.5 img/sec | Face Detection | 270.8 img/sec |
| 4.35 Gpixels/sec | Horizon Detection | 9.23 Gpixels/sec |
| 5.67 Gpixels/sec | Edge Detection | 13.7 Gpixels/sec |
| 6.44 Gpixels/sec | Gaussian Blur | 11.1 Gpixels/sec |
| 1.36 Gpixels/sec | Feature Matching | 1.74 Gpixels/sec |
| 528.5 Gpixels/sec | Stereo Matching | 871 Gpixels/sec |
| 16372.3 FPS | Particle Physics | 29891.2 FPS |
| OpenCL | API | OpenCL |
| 19527 | G3D Mark Score | 31406 |
| 767 | G2D Mark | 1285 |
| 178 FPS | DirectX 11 | 356 FPS |
| 85 FPS | DirectX 12 | 133 FPS |
| 8389 Ops/s | GPU Compute | 17768 Ops/s |
| 21186 | GB6 ML Single Precision | 42092 |
| 34404 | GB6 ML Half Precision | 50673 |
| 16559 | GB6 ML Quantized | 32874 |
| 8642 | Image Classification (SP) | 18608 |
| 20635 | Image Segmentation (HP) | 25385 |
| 26378 | Image Super Resolution (Q) | 45641 |
| 39776 | Face Detection (HP) | 71321 |
| 105983 | Pose Estimation (Q) | 257258 |
| 2995 | Text Classification (SP) | 5240 |
| 4507 | Machine Translation (HP) | 7425 |
| 10198 | Object Detection (SP) | 21335 |
| 41078 | Depth Estimation (Q) | 66140 |
| 190315 | Style Transfer (SP) | 483867 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 59-104 GPixel/s | Pixel Fill Rate | 480 GPixel/s |
| 177-313 GTexel/s | Texture Fill Rate | 959 GTexel/s |
| 11.3-20 TFLOPS | FLOPS (FP32) | 61.4 TFLOPS |
| GDDR6 | Memory Type | GDDR6 |
| 8 GB | Memory Size | 24 GB |
| 2000 MHz | Memory Clock | 2500 MHz |
| 16000 Mbps | Effective Memory Speed | 20000 Mbps |
| 128-bit | Bus | 384-bit |
| No | ECC | No |
| 256 GB/s | Memory Bandwidth | 960 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 35-140 W (configurable) | TGP | 355 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 5 nm |
| 186 mm² | Die Size | 529 mm² |
| 22.9 billion | Transistor Count | 57 billion |
| 123.12 MTr/mm² | Transistor Density | 107.75 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.2 |
| 8.9 | CUDA | — |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Nvidia | Vendor | Amd |
| Discrete | Build | Discrete |
| February 22, 2023 | Released | November 3, 2022 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| Ada Lovelace | Architecture | RDNA 3.0 |
| AD106 (GN21-X6) | GPU Codename | Navi 31 |
| -Intel Core Ultra 7 155Hor above | Recommended CPU | -Intel Core i7 13700Kor above |
| 12729 | Steel Nomad Lite Score | 29870 |
| 12518 | Time Spy | 30766 |
| 54826 | Solar Bay | 123758 |
| 7403 | Port Royal | 16749 |
| 30044 | Fire Strike | 73217 |
| 23244 | Wild Life Extreme | 58530 |
| 113720 | Night Raid | 184767 |
| 735-2070 MHz (configurable) | Base Clock | 1929 MHz |
| 1230-2175 MHz (configurable) | Boost Clock | 2498 MHz |
| 4608 | Shading Units | 6144 |
| 144 | Texture Mapping Units (TMUs) | 384 |
| 48 | Render Output Units (ROPs) | 192 |
| 36 | Compute Units (Pipelines) | — |
| 144 | Tensor Cores | — |
| 36 | Ray-tracing Cores | 96 |
| 128KB per cluster | L1 Cache | 256KB per cluster |
| 32MB shared | L2 Cache | 6MB shared |
| 2 IPC | Instructions Per Cycle | 4 IPC |
Compare with something else?
Compare GeForce RTX 4070 with another →