Quick/Comparisons
80 | Gaming | 11 |
71 | Workstation | 16 |
66 | AI/ML |
Compare with something else?
Compare GeForce RTX 4080 with another →16 |
43 | Energy Efficiency | 85 |
75 | Quick Comparison Final Score | 25 |
| AD103 | Graphics Processor | Strix Point |
| 9728 | Cores | 768 |
| 304 / 112 | TMUs / ROPs | 48 / 16 |
| 8710.73 | Blender GPU | 277.09 |
| — | Forza Horizon 5 | 30 |
| — | The Witcher 3 | 26 |
| — | Counter-Strike 2 | 30 |
| — | Far Cry 6 | 37 |
| — | Hogwarts Legacy | 18 |
| — | Call of Duty | 32 |
| — | Ghost of Tsushima | 16 |
| — | Cyberpunk 2077 | 20 |
| — | Tomb Raider | 35 |
| — | Average FPS | 27 |
| — | 1080p High | 37 |
| — | 1080p Ultra | 27 |
| — | 1440p Ultra | 18 |
| — | 4K Ultra | 9 |
| — | Margin of Error | Low |
| 217712 | GB6 Compute Score | 37347 |
| 250.4 img/sec | Background Blur | 72 img/sec |
| 190 img/sec | Face Detection | 35.7 img/sec |
| 9.56 Gpixels/sec | Horizon Detection | 1.04 Gpixels/sec |
| 12.8 Gpixels/sec | Edge Detection | 1.33 Gpixels/sec |
| 15.3 Gpixels/sec | Gaussian Blur | 1.17 Gpixels/sec |
| 1.97 Gpixels/sec | Feature Matching | 0.44 Gpixels/sec |
| 1130 Gpixels/sec | Stereo Matching | 115.5 Gpixels/sec |
| 28795.5 FPS | Particle Physics | 4880.8 FPS |
| OpenCL | API | OpenCL |
| 34430 | G3D Mark Score | 7689 |
| 1250 | G2D Mark | 972 |
| 313 FPS | DirectX 11 | 74 FPS |
| 132 FPS | DirectX 12 | 32 FPS |
| 20406 Ops/s | GPU Compute | 3743 Ops/s |
| 36799 | GB6 ML Single Precision | 8534 |
| 53331 | GB6 ML Half Precision | 12638 |
| 28104 | GB6 ML Quantized | 6209 |
| 13466 | Image Classification (SP) | 3202 |
| 34767 | Image Segmentation (HP) | 5252 |
| 42687 | Image Super Resolution (Q) | 9782 |
| 70927 | Face Detection (HP) | 11315 |
| 239350 | Pose Estimation (Q) | 30704 |
| 3606 | Text Classification (SP) | 2351 |
| 6519 | Machine Translation (HP) | 4339 |
| 18153 | Object Detection (SP) | 2843 |
| 65667 | Depth Estimation (Q) | 14243 |
| 414848 | Style Transfer (SP) | 69169 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 281 GPixel/s | Pixel Fill Rate | 46 GPixel/s |
| 762 GTexel/s | Texture Fill Rate | 139 GTexel/s |
| 48.7 TFLOPS | FLOPS (FP32) | 4.5 TFLOPS |
| GDDR6X | Memory Type | System Shared |
| 16 GB | Memory Size | — |
| 1400 MHz | Memory Clock | — |
| 22400 Mbps | Effective Memory Speed | — |
| 256-bit | Bus | — |
| No | ECC | — |
| 716.8 GB/s | Memory Bandwidth | — |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 320 W | TGP | 15-54 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 4 nm |
| 379 mm² | Die Size | 233 mm² |
| 45 billion | Transistor Count | 34 billion |
| 118.73 MTr/mm² | Transistor Density | 145.92 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.1 |
| 8.9 | CUDA | No |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| September 20, 2022 | Released | June 3, 2024 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Generic |
| High-end | Segment | Mid-range |
| Ada Lovelace | Architecture | RDNA 3.5 |
| AD103 | GPU Codename | Strix Point |
| -Intel Core i7 14700Kor above | Recommended CPU | -AMD Ryzen AI 9 365or above |
| 30172 | Steel Nomad Lite Score | 2998 |
| 28161 | Time Spy | 3120 |
| 136931 | Solar Bay | 14257 |
| 17982 | Port Royal | 1413 |
| 64633 | Fire Strike | 8603 |
| 59111 | Wild Life Extreme | 6313 |
| 184963 | Night Raid | 38054 |
| 2205 MHz | Base Clock | 400 MHz |
| 2505 MHz | Boost Clock | 2900 MHz |
| 9728 | Shading Units | 768 |
| 304 | Texture Mapping Units (TMUs) | 48 |
| 112 | Render Output Units (ROPs) | 16 |
| 76 | Compute Units (Pipelines) | 12 |
| 304 | Tensor Cores | No |
| 76 | Ray-tracing Cores | 12 |
| 128KB per cluster | L1 Cache | 512KB per cluster |
| 64MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |