Quick/Comparisons
78 | Gaming | 5 |
76 | Workstation | 13 |
66 | AI/ML |
Compare with something else?
Compare GeForce RTX 4080 with another →6 |
46 | Energy Efficiency | 75 |
75 | Quick Comparison Final Score | 19 |
| AD103 | Graphics Processor | — |
| 10240 | Cores | 448 |
| 320 / 112 | TMUs / ROPs | 28 / 8 |
| 8420.48 | Blender GPU | — |
| 171 | Forza Horizon 5 | 10 |
| 210 | The Witcher 3 | — |
| 223 | Counter-Strike 2 | 14 |
| 166 | Far Cry 6 | 11 |
| 137 | Hogwarts Legacy | - |
| 216 | Call of Duty | 13 |
| 122 | Ghost of Tsushima | - |
| 177 | Cyberpunk 2077 | - |
| 265 | Tomb Raider | 11 |
| 187 | Average FPS | 10 |
| 221 | 1080p High | 13 |
| 187 | 1080p Ultra | 10 |
| 149 | 1440p Ultra | - |
| 87 | 4K Ultra | - |
| Low | Margin of Error | Low |
| 250691 | GB6 Compute Score | 14408 |
| 279.5 img/sec | Background Blur | 33.7 img/sec |
| 220.1 img/sec | Face Detection | 15.4 img/sec |
| 11 Gpixels/sec | Horizon Detection | 0.35 Gpixels/sec |
| 15.2 Gpixels/sec | Edge Detection | 0.76 Gpixels/sec |
| 16.2 Gpixels/sec | Gaussian Blur | 0.69 Gpixels/sec |
| 2.08 Gpixels/sec | Feature Matching | 0.21 Gpixels/sec |
| 1370 Gpixels/sec | Stereo Matching | 54.7 Gpixels/sec |
| 37199.7 FPS | Particle Physics | 1957.6 FPS |
| OpenCL | API | OpenCL |
| 34252 | G3D Mark Score | 2250 |
| 1278 | G2D Mark | 568 |
| 300 FPS | DirectX 11 | 16 FPS |
| 134 FPS | DirectX 12 | 11 FPS |
| 19639 Ops/s | GPU Compute | 1215 Ops/s |
| 36883 | GB6 ML Single Precision | 3157 |
| 54286 | GB6 ML Half Precision | 4191 |
| 28474 | GB6 ML Quantized | 2365 |
| 12453 | Image Classification (SP) | 1323 |
| 34467 | Image Segmentation (HP) | 1675 |
| 43534 | Image Super Resolution (Q) | 2919 |
| 70300 | Face Detection (HP) | 4386 |
| 242331 | Pose Estimation (Q) | 9348 |
| 3767 | Text Classification (SP) | 1024 |
| 6614 | Machine Translation (HP) | 1888 |
| 18301 | Object Detection (SP) | 1452 |
| 66477 | Depth Estimation (Q) | 5272 |
| 417906 | Style Transfer (SP) | 19585 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 286 GPixel/s | Pixel Fill Rate | 12-16 GPixel/s |
| 816 GTexel/s | Texture Fill Rate | 42-56 GTexel/s |
| 52.2 TFLOPS | FLOPS (FP32) | 1.3-1.8 TFLOPS |
| GDDR6X | Memory Type | System Shared |
| 16 GB | Memory Size | System RAM Dependent |
| 1438 MHz | Memory Clock | System RAM Dependent |
| 23000 Mbps | Effective Memory Speed | System RAM Dependent |
| 256-bit | Bus | — |
| No | ECC | No |
| 736.3 GB/s | Memory Bandwidth | — |
| PCIe 4.0 x16 | Interface | IGP |
| 320 W | TGP | 10-45 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 7 nm |
| 379 mm² | Die Size | — |
| 45 billion | Transistor Count | — |
| 118.73 MTr/mm² | Transistor Density | — |
| 12 | DirectX | 12.1 |
| 1.3 | Vulkan | — |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.2 |
| 8.9 | CUDA | — |
| Yes | Ray Tracing | No |
| DLSS 3 | DLSS | No |
| 1.4a | DisplayPort | — |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| January 31, 2024 | Released | January 7, 2020 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Generic |
| High-end | Segment | Entry-level |
| Ada Lovelace | Architecture | Raven |
| AD103 | GPU Codename | — |
| -Intel Core i7 14700Kor above | Recommended CPU | -AMD Ryzen 5 5500Uor above |
| 30711 | Steel Nomad Lite Score | 943 |
| 28279 | Time Spy | 1068 |
| 138998 | Solar Bay | — |
| 18348 | Port Royal | — |
| 63714 | Fire Strike | 3396 |
| 60015 | Wild Life Extreme | 2015 |
| 180412 | Night Raid | 13093 |
| 2295 MHz | Base Clock | 300 MHz |
| 2550 MHz | Boost Clock | 1500-2000 MHz (configurable) |
| 10240 | Shading Units | 448 |
| 320 | Texture Mapping Units (TMUs) | 28 |
| 112 | Render Output Units (ROPs) | 8 |
| 80 | Compute Units (Pipelines) | 7 |
| 320 | Tensor Cores | No |
| 80 | Ray-tracing Cores | No |
| 128KB per cluster | L1 Cache | — |
| 64MB shared | L2 Cache | — |
| 2 IPC | Instructions Per Cycle | 2 IPC |