Quick/Comparisons
66 | Gaming | 22 |
73 | Workstation | 29 |
52 | AI/ML |
Compare with something else?
Compare GeForce RTX 3090 with another →21 |
37 | Energy Efficiency | 45 |
66 | Quick Comparison Final Score | 25 |
| GA102 | Graphics Processor | Navi 10 |
| 10752 | Cores | 2304 |
| 336 / 112 | TMUs / ROPs | 144 / 64 |
| 6057.83 | Blender GPU | 619.59 |
| 141 | Forza Horizon 5 | 60 |
| 182 | The Witcher 3 | 79 |
| 210 | Counter-Strike 2 | 105 |
| 147 | Far Cry 6 | 73 |
| 112 | Hogwarts Legacy | 46 |
| 173 | Call of Duty | 67 |
| 108 | Ghost of Tsushima | 46 |
| 143 | Cyberpunk 2077 | 47 |
| 243 | Tomb Raider | 88 |
| 162 | Average FPS | 68 |
| 128 | 1440p Ultra | 46 |
| 75 | 4K Ultra | 25 |
| Low | Margin of Error | Low |
| 193 | 1080p High | 88 |
| 162 | 1080p Ultra | 68 |
| 232083 | GB6 Compute Score | 66629 |
| 362.7 img/sec | Background Blur | 123.2 img/sec |
| 227.9 img/sec | Face Detection | 71.4 img/sec |
| 11.3 Gpixels/sec | Horizon Detection | 2.85 Gpixels/sec |
| 15.9 Gpixels/sec | Edge Detection | 4.1 Gpixels/sec |
| 12.1 Gpixels/sec | Gaussian Blur | 3.48 Gpixels/sec |
| 1.56 Gpixels/sec | Feature Matching | 0.62 Gpixels/sec |
| 1080 Gpixels/sec | Stereo Matching | 253.9 Gpixels/sec |
| 31024.6 FPS | Particle Physics | 7670.6 FPS |
| OpenCL | API | OpenCL |
| 29288 | G3D Mark Score | 13410 |
| 1226 | G2D Mark | 872 |
| 238 FPS | DirectX 11 | 96 FPS |
| 122 FPS | DirectX 12 | 52 FPS |
| 16569 Ops/s | GPU Compute | 6222 Ops/s |
| 26701 | GB6 ML Single Precision | 12529 |
| 38573 | GB6 ML Half Precision | 14594 |
| 15995 | GB6 ML Quantized | 9434 |
| 10246 | Image Classification (SP) | 5459 |
| 22830 | Image Segmentation (HP) | 6448 |
| 23532 | Image Super Resolution (Q) | 15013 |
| 48657 | Face Detection (HP) | 17318 |
| 147241 | Pose Estimation (Q) | 62592 |
| 2917 | Text Classification (SP) | 1533 |
| 4427 | Machine Translation (HP) | 3771 |
| 13323 | Object Detection (SP) | 5601 |
| 40055 | Depth Estimation (Q) | 22988 |
| 298683 | Style Transfer (SP) | 120386 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 208 GPixel/s | Pixel Fill Rate | 100 GPixel/s |
| 625 GTexel/s | Texture Fill Rate | 225 GTexel/s |
| 40 TFLOPS | FLOPS (FP32) | 7.2 TFLOPS |
| GDDR6X | Memory Type | GDDR6 |
| 24 GB | Memory Size | 6 GB |
| 1313 MHz | Memory Clock | 1500 MHz |
| 21000 Mbps | Effective Memory Speed | 12000 Mbps |
| 384-bit | Bus | 192-bit |
| No | ECC | No |
| 1008 GB/s | Memory Bandwidth | 288 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 450 W | TGP | 150 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 7 nm |
| 628 mm² | Die Size | 251 mm² |
| 28 billion | Transistor Count | 10 billion |
| 44.59 MTr/mm² | Transistor Density | 39.84 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.1 |
| 8.6 | CUDA | — |
| Yes | Ray Tracing | No |
| DLSS 2 | DLSS | No |
| 1.4a | DisplayPort | 1.4a |
| Nvidia | Vendor | Amd |
| Discrete | Build | Discrete |
| March 29, 2022 | Released | January 21, 2020 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | Mid-range |
| Ampere | Architecture | RDNA 1.0 |
| GA102 | GPU Codename | Navi 10 |
| -Intel Core i9 12900Kor above | Recommended CPU | -Intel Core i5 9500or above |
| 24378 | Steel Nomad Lite Score | 6995 |
| 21854 | Time Spy | 7632 |
| 109167 | Solar Bay | — |
| 14888 | Port Royal | — |
| 51943 | Fire Strike | 22322 |
| 48864 | Wild Life Extreme | 14669 |
| 156500 | Night Raid | 86737 |
| 1560 MHz | Base Clock | 1130 MHz |
| 1860 MHz | Boost Clock | 1560 MHz |
| 10752 | Shading Units | 2304 |
| 336 | Texture Mapping Units (TMUs) | 144 |
| 112 | Render Output Units (ROPs) | 64 |
| 84 | Compute Units (Pipelines) | — |
| 336 | Tensor Cores | No |
| 84 | Ray-tracing Cores | No |
| 128KB per cluster | L1 Cache | — |
| 6MB shared | L2 Cache | 3MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |