Quick/Comparisons
61 | Gaming | 80 |
69 | Workstation | 71 |
53 | AI/ML |
Compare with something else?
Compare GeForce RTX 3090 with another →66 |
35 | Energy Efficiency | 43 |
62 | Quick Comparison Final Score | 75 |
| GA102 | Graphics Processor | AD103 |
| 10496 | Cores | 9728 |
| 328 / 112 | TMUs / ROPs | 304 / 112 |
| 5800.59 | Blender GPU | 8710.73 |
| 125 | Forza Horizon 5 | — |
| 175 | The Witcher 3 | — |
| 212 | Counter-Strike 2 | — |
| 142 | Far Cry 6 | — |
| 106 | Hogwarts Legacy | — |
| 159 | Call of Duty | — |
| 97 | Ghost of Tsushima | — |
| 132 | Cyberpunk 2077 | — |
| 226 | Tomb Raider | — |
| 153 | Average FPS | — |
| 179 | 1080p High | — |
| 153 | 1080p Ultra | — |
| 119 | 1440p Ultra | — |
| 70 | 4K Ultra | — |
| Low | Margin of Error | — |
| 211669 | GB6 Compute Score | 217712 |
| 320.8 img/sec | Background Blur | 250.4 img/sec |
| 207.2 img/sec | Face Detection | 190 img/sec |
| 10.1 Gpixels/sec | Horizon Detection | 9.56 Gpixels/sec |
| 14.4 Gpixels/sec | Edge Detection | 12.8 Gpixels/sec |
| 11.5 Gpixels/sec | Gaussian Blur | 15.3 Gpixels/sec |
| 1.48 Gpixels/sec | Feature Matching | 1.97 Gpixels/sec |
| 984.2 Gpixels/sec | Stereo Matching | 1130 Gpixels/sec |
| 27764.9 FPS | Particle Physics | 28795.5 FPS |
| OpenCL | API | OpenCL |
| 26551 | G3D Mark Score | 34430 |
| 1069 | G2D Mark | 1250 |
| 218 FPS | DirectX 11 | 313 FPS |
| 110 FPS | DirectX 12 | 132 FPS |
| 15117 Ops/s | GPU Compute | 20406 Ops/s |
| 27237 | GB6 ML Single Precision | 36799 |
| 41500 | GB6 ML Half Precision | 53331 |
| 15927 | GB6 ML Quantized | 28104 |
| 10665 | Image Classification (SP) | 13466 |
| 28963 | Image Segmentation (HP) | 34767 |
| 22697 | Image Super Resolution (Q) | 42687 |
| 55232 | Face Detection (HP) | 70927 |
| 128155 | Pose Estimation (Q) | 239350 |
| 3152 | Text Classification (SP) | 3606 |
| 5088 | Machine Translation (HP) | 6519 |
| 13891 | Object Detection (SP) | 18153 |
| 37984 | Depth Estimation (Q) | 65667 |
| 272000 | Style Transfer (SP) | 414848 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 190 GPixel/s | Pixel Fill Rate | 281 GPixel/s |
| 556 GTexel/s | Texture Fill Rate | 762 GTexel/s |
| 35.6 TFLOPS | FLOPS (FP32) | 48.7 TFLOPS |
| GDDR6X | Memory Type | GDDR6X |
| 24 GB | Memory Size | 16 GB |
| 1219 MHz | Memory Clock | 1400 MHz |
| 19500 Mbps | Effective Memory Speed | 22400 Mbps |
| 384-bit | Bus | 256-bit |
| No | ECC | No |
| 936.2 GB/s | Memory Bandwidth | 716.8 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 350 W | TGP | 320 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 5 nm |
| 628 mm² | Die Size | 379 mm² |
| 28 billion | Transistor Count | 45 billion |
| 44.59 MTr/mm² | Transistor Density | 118.73 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.6 | CUDA | 8.9 |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | DLSS 3 |
| 1.4a | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| September 24, 2020 | Released | September 20, 2022 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| Ampere | Architecture | Ada Lovelace |
| GA102 | GPU Codename | AD103 |
| -Intel Core i9 12900Kor above | Recommended CPU | -Intel Core i7 14700Kor above |
| 21851 | Steel Nomad Lite Score | 30172 |
| 19896 | Time Spy | 28161 |
| 97375 | Solar Bay | 136931 |
| 13631 | Port Royal | 17982 |
| 47515 | Fire Strike | 64633 |
| 43673 | Wild Life Extreme | 59111 |
| 139755 | Night Raid | 184963 |
| 1395 MHz | Base Clock | 2205 MHz |
| 1695 MHz | Boost Clock | 2505 MHz |
| 10496 | Shading Units | 9728 |
| 328 | Texture Mapping Units (TMUs) | 304 |
| 112 | Render Output Units (ROPs) | 112 |
| 82 | Compute Units (Pipelines) | 76 |
| 328 | Tensor Cores | 304 |
| 82 | Ray-tracing Cores | 76 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 6MB shared | L2 Cache | 64MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |