Quick/Comparisons
The GeForce RTX 4080 excels in gaming performance with an 80 score, significantly outpacing the GeForce RTX 5070 Laptop's 45 score.
The GeForce RTX 4080 takes the lead in content creation with a 71 score, thanks to its larger 16GB memory pool and better workstation capabilities.
The GeForce RTX 4080's 66 score in AI/ML outperforms the GeForce RTX 5070 Laptop's 39 score, likely due to its more advanced Ada Lovelace architecture.
80 | Gaming | 45 |
71 | Workstation | 45 |
66 | AI/ML | 39 |
43 | Energy Efficiency | 65 |
75 | Quick Comparison Final Score | 48 |
| AD103 | Graphics Processor | GB206-300 |
| 9728 | Cores | 4608 |
| 304 / 112 | TMUs / ROPs | 144 / 48 |
| 8710.73 | Blender GPU | 4007.35 |
| — | Forza Horizon 5 | 96 |
| — | The Witcher 3 | 137 |
| — | Counter-Strike 2 | 195 |
| — | Far Cry 6 | 116 |
| — | Hogwarts Legacy | 79 |
| — | Call of Duty | 110 |
| — | Ghost of Tsushima | 73 |
| — | Cyberpunk 2077 | 92 |
| — | Tomb Raider | 149 |
| — | Average FPS | 116 |
| — | 1080p High | 140 |
| — | 1080p Ultra | 116 |
| — | 1440p Ultra | 88 |
| — | 4K Ultra | 51 |
| — | Margin of Error | Low |
| 217712 | GB6 Compute Score | 134209 |
| 250.4 img/sec | Background Blur | 213.4 img/sec |
| 190 img/sec | Face Detection | 130.4 img/sec |
| 9.56 Gpixels/sec | Horizon Detection | 4.89 Gpixels/sec |
| 12.8 Gpixels/sec | Edge Detection | 6.23 Gpixels/sec |
| 15.3 Gpixels/sec | Gaussian Blur | 7.41 Gpixels/sec |
| 1.97 Gpixels/sec | Feature Matching | 1.46 Gpixels/sec |
| 1130 Gpixels/sec | Stereo Matching | 661.9 Gpixels/sec |
| 28795.5 FPS | Particle Physics | 19395.6 FPS |
| OpenCL | API | OpenCL |
| 34430 | G3D Mark Score | 19173 |
| 1250 | G2D Mark | 884 |
| 313 FPS | DirectX 11 | 186 FPS |
| 132 FPS | DirectX 12 | 91 FPS |
| 20406 Ops/s | GPU Compute | 7114 Ops/s |
| 36799 | GB6 ML Single Precision | 22022 |
| 53331 | GB6 ML Half Precision | 40929 |
| 28104 | GB6 ML Quantized | 17069 |
| 13466 | Image Classification (SP) | 8984 |
| 34767 | Image Segmentation (HP) | 26270 |
| 42687 | Image Super Resolution (Q) | 24606 |
| 70927 | Face Detection (HP) | 48283 |
| 239350 | Pose Estimation (Q) | 98180 |
| 3606 | Text Classification (SP) | 3260 |
| 6519 | Machine Translation (HP) | 5770 |
| 18153 | Object Detection (SP) | 11172 |
| 65667 | Depth Estimation (Q) | 43305 |
| 414848 | Style Transfer (SP) | 165555 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 281 GPixel/s | Pixel Fill Rate | 68-121 GPixel/s |
| 762 GTexel/s | Texture Fill Rate | 203-363 GTexel/s |
| 48.7 TFLOPS | FLOPS (FP32) | 13-23.2 TFLOPS |
| GDDR6X | Memory Type | GDDR7 |
| 16 GB | Memory Size | 8 GB |
| 1400 MHz | Memory Clock | 1750 MHz |
| 22400 Mbps | Effective Memory Speed | 24000 Mbps |
| 256-bit | Bus | 128-bit |
| No | ECC | No |
| 716.8 GB/s | Memory Bandwidth | 384 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 5.0 x16 |
| 320 W | TGP | 50-125 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 4 nm |
| 379 mm² | Die Size | 181 mm² |
| 45 billion | Transistor Count | 21.9 billion |
| 118.73 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 |
| 8.9 | CUDA | 12 |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | DLSS 4 |
| 1.4a | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| September 20, 2022 | Released | January 7, 2025 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Gaming |
| High-end | Segment | Mid-range |
| Ada Lovelace | Architecture | Blackwell 2.0 |
| AD103 | GPU Codename | GB206-300 |
| -Intel Core i7 14700Kor above | Recommended CPU | -Intel Core Ultra 7 255HXor above |
| 30172 | Steel Nomad Lite Score | 13896 |
| 28161 | Time Spy | 13563 |
| 136931 | Solar Bay | 59662 |
| 17982 | Port Royal | 8648 |
| 64633 | Fire Strike | 35860 |
| 59111 | Wild Life Extreme | 24526 |
| 184963 | Night Raid | 125756 |
| 2205 MHz | Base Clock | 890-1410 MHz (configurable) |
| 2505 MHz | Boost Clock | 1410-2520 MHz (configurable) |
| 9728 | Shading Units | 4608 |
| 304 | Texture Mapping Units (TMUs) | 144 |
| 112 | Render Output Units (ROPs) | 48 |
| 76 | Compute Units (Pipelines) | 36 |
| 304 | Tensor Cores | 144 |
| 76 | Ray-tracing Cores | 36 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 64MB shared | L2 Cache | 32MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 4080 with another →