Quick/Comparisons
The GeForce RTX 4090 outperforms the GeForce RTX 4070 Laptop in gaming by a significant margin, thanks to its superior architecture and increased memory capacity.
The GeForce RTX 4090 excels in content creation with its strong workstation performance and 24GB of GDDR6X memory, outpacing the GeForce RTX 4070 Laptop.
The GeForce RTX 4090's capable AI/ML compute capabilities and 24GB of GDDR6X memory give it an edge over the GeForce RTX 4070 Laptop in AI and machine learning tasks.
41 | Gaming | 92 |
40 | Workstation | 91 |
38 | AI/ML | 76 |
56 | Energy Efficiency | 43 |
43 | Quick Comparison Final Score | 89 |
| AD106 (GN21-X6) | Graphics Processor | AD102 |
| 4608 | Cores | 16384 |
| 144 / 48 | TMUs / ROPs | 512 / 176 |
| 3587.08 | Blender GPU | 11688.48 |
| 90 | Forza Horizon 5 | 203 |
| 132 | The Witcher 3 | 270 |
| 178 | Counter-Strike 2 | 245 |
| 112 | Far Cry 6 | 183 |
| 75 | Hogwarts Legacy | 165 |
| 104 | Call of Duty | 269 |
| 68 | Ghost of Tsushima | 150 |
| 87 | Cyberpunk 2077 | 204 |
| 139 | Tomb Raider | 283 |
| 109 | Average FPS | 219 |
| 131 | 1080p High | 256 |
| 109 | 1080p Ultra | 219 |
| 81 | 1440p Ultra | 176 |
| 46 | 4K Ultra | 107 |
| Low | Margin of Error | Low |
| 115081 | GB6 Compute Score | 316301 |
| 158.5 img/sec | Background Blur | 318.9 img/sec |
| 116.5 img/sec | Face Detection | 222.8 img/sec |
| 4.35 Gpixels/sec | Horizon Detection | 14.2 Gpixels/sec |
| 5.67 Gpixels/sec | Edge Detection | 21 Gpixels/sec |
| 6.44 Gpixels/sec | Gaussian Blur | 23.9 Gpixels/sec |
| 1.36 Gpixels/sec | Feature Matching | 2.38 Gpixels/sec |
| 528.5 Gpixels/sec | Stereo Matching | 1950 Gpixels/sec |
| 16372.3 FPS | Particle Physics | 48090.4 FPS |
| OpenCL | API | OpenCL |
| 19527 | G3D Mark Score | 38071 |
| 767 | G2D Mark | 1303 |
| 178 FPS | DirectX 11 | 324 FPS |
| 85 FPS | DirectX 12 | 151 FPS |
| 8389 Ops/s | GPU Compute | 26193 Ops/s |
| 21186 | GB6 ML Single Precision | 42962 |
| 34404 | GB6 ML Half Precision | 59636 |
| 16559 | GB6 ML Quantized | 31670 |
| 8642 | Image Classification (SP) | 15600 |
| 20635 | Image Segmentation (HP) | 36657 |
| 26378 | Image Super Resolution (Q) | 48114 |
| 39776 | Face Detection (HP) | 78111 |
| 105983 | Pose Estimation (Q) | 289639 |
| 2995 | Text Classification (SP) | 4074 |
| 4507 | Machine Translation (HP) | 6349 |
| 10198 | Object Detection (SP) | 21186 |
| 41078 | Depth Estimation (Q) | 75599 |
| 190315 | Style Transfer (SP) | 601428 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 59-104 GPixel/s | Pixel Fill Rate | 444 GPixel/s |
| 177-313 GTexel/s | Texture Fill Rate | 1290 GTexel/s |
| 11.3-20 TFLOPS | FLOPS (FP32) | 82.6 TFLOPS |
| GDDR6 | Memory Type | GDDR6X |
| 8 GB | Memory Size | 24 GB |
| 2000 MHz | Memory Clock | 2625 MHz |
| 16000 Mbps | Effective Memory Speed | 21000 Mbps |
| 128-bit | Bus | 384-bit |
| No | ECC | No |
| 256 GB/s | Memory Bandwidth | 1010 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 35-140 W (configurable) | TGP | 450 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 5 nm |
| 186 mm² | Die Size | 609 mm² |
| 22.9 billion | Transistor Count | 76.3 billion |
| 123.12 MTr/mm² | Transistor Density | 125.29 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.9 | CUDA | 8.9 |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | DLSS 3 |
| 1.4a | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| February 22, 2023 | Released | September 20, 2022 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| Ada Lovelace | Architecture | Ada Lovelace |
| AD106 (GN21-X6) | GPU Codename | AD102 |
| -Intel Core Ultra 7 155Hor above | Recommended CPU | -Intel Core i9 14900Kor above |
| 12729 | Steel Nomad Lite Score | 42169 |
| 12518 | Time Spy | 36311 |
| 54826 | Solar Bay | 187386 |
| 7403 | Port Royal | 26128 |
| 30044 | Fire Strike | 72387 |
| 23244 | Wild Life Extreme | 85230 |
| 113720 | Night Raid | 195880 |
| 735-2070 MHz (configurable) | Base Clock | 2235 MHz |
| 1230-2175 MHz (configurable) | Boost Clock | 2520 MHz |
| 4608 | Shading Units | 16384 |
| 144 | Texture Mapping Units (TMUs) | 512 |
| 48 | Render Output Units (ROPs) | 176 |
| 36 | Compute Units (Pipelines) | 128 |
| 144 | Tensor Cores | 512 |
| 36 | Ray-tracing Cores | 128 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 32MB shared | L2 Cache | 72MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 4070 with another →