Quick/Comparisons
The GeForce RTX 4090 takes the lead in gaming performance, thanks to its significantly higher score of 92, outpacing the GeForce RTX 3080 Ti's score of 60.
The GeForce RTX 4090 edges out the GeForce RTX 3080 Ti in content creation, boasting a score of 91 compared to the GeForce RTX 3080 Ti's score of 64.
The GeForce RTX 4090 outperforms the GeForce RTX 3080 Ti in AI/ML compute, with a score of 76, leaving the GeForce RTX 3080 Ti's score of 46 in its wake.
60 | Gaming | 92 |
64 | Workstation | 91 |
46 | AI/ML |
Compare with something else?
Compare GeForce RTX 3080 with another →76 |
35 | Energy Efficiency | 43 |
59 | Quick Comparison Final Score | 89 |
| GA102 | Graphics Processor | AD102 |
| 10240 | Cores | 16384 |
| 320 / 112 | TMUs / ROPs | 512 / 176 |
| 5565.9 | Blender GPU | 11688.48 |
| 128 | Forza Horizon 5 | 203 |
| 174 | The Witcher 3 | 270 |
| 205 | Counter-Strike 2 | 245 |
| 139 | Far Cry 6 | 183 |
| 108 | Hogwarts Legacy | 165 |
| 161 | Call of Duty | 269 |
| 96 | Ghost of Tsushima | 150 |
| 128 | Cyberpunk 2077 | 204 |
| 219 | Tomb Raider | 283 |
| 151 | Average FPS | 219 |
| 180 | 1080p High | 256 |
| 151 | 1080p Ultra | 219 |
| 117 | 1440p Ultra | 176 |
| 69 | 4K Ultra | 107 |
| Low | Margin of Error | Low |
| 196756 | GB6 Compute Score | 316301 |
| 239.8 img/sec | Background Blur | 318.9 img/sec |
| 156.8 img/sec | Face Detection | 222.8 img/sec |
| 10.8 Gpixels/sec | Horizon Detection | 14.2 Gpixels/sec |
| 14.8 Gpixels/sec | Edge Detection | 21 Gpixels/sec |
| 11.9 Gpixels/sec | Gaussian Blur | 23.9 Gpixels/sec |
| 1.53 Gpixels/sec | Feature Matching | 2.38 Gpixels/sec |
| 889.6 Gpixels/sec | Stereo Matching | 1950 Gpixels/sec |
| 26054.6 FPS | Particle Physics | 48090.4 FPS |
| OpenCL | API | OpenCL |
| 26777 | G3D Mark Score | 38071 |
| 1095 | G2D Mark | 1303 |
| 222 FPS | DirectX 11 | 324 FPS |
| 109 FPS | DirectX 12 | 151 FPS |
| 15025 Ops/s | GPU Compute | 26193 Ops/s |
| 25945 | GB6 ML Single Precision | 42962 |
| 38430 | GB6 ML Half Precision | 59636 |
| 15331 | GB6 ML Quantized | 31670 |
| 9747 | Image Classification (SP) | 15600 |
| 26654 | Image Segmentation (HP) | 36657 |
| 21475 | Image Super Resolution (Q) | 48114 |
| 49813 | Face Detection (HP) | 78111 |
| 135370 | Pose Estimation (Q) | 289639 |
| 2796 | Text Classification (SP) | 4074 |
| 4757 | Machine Translation (HP) | 6349 |
| 12924 | Object Detection (SP) | 21186 |
| 36756 | Depth Estimation (Q) | 75599 |
| 274032 | Style Transfer (SP) | 601428 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 186 GPixel/s | Pixel Fill Rate | 444 GPixel/s |
| 533 GTexel/s | Texture Fill Rate | 1290 GTexel/s |
| 34.1 TFLOPS | FLOPS (FP32) | 82.6 TFLOPS |
| GDDR6X | Memory Type | GDDR6X |
| 12 GB | Memory Size | 24 GB |
| 1188 MHz | Memory Clock | 2625 MHz |
| 19000 Mbps | Effective Memory Speed | 21000 Mbps |
| 384-bit | Bus | 384-bit |
| No | ECC | No |
| 912 GB/s | Memory Bandwidth | 1010 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 350 W | TGP | 450 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 5 nm |
| 628 mm² | Die Size | 609 mm² |
| 28 billion | Transistor Count | 76.3 billion |
| 44.59 MTr/mm² | Transistor Density | 125.29 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 |
| January 3, 2021 | Released | September 20, 2022 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| Ampere | Architecture | Ada Lovelace |
| GA102 | GPU Codename | AD102 |
| -Intel Core i9 12900Kor above | Recommended CPU | -Intel Core i9 14900Kor above |
| 21408 | Steel Nomad Lite Score | 42169 |
| 19632 | Time Spy | 36311 |
| 96597 | Solar Bay | 187386 |
| 13265 | Port Royal | 26128 |
| 47867 | Fire Strike | 72387 |
| 42716 | Wild Life Extreme | 85230 |
| 144955 | Night Raid | 195880 |
| 1365 MHz | Base Clock | 2235 MHz |
| 1665 MHz | Boost Clock | 2520 MHz |
| 10240 | Shading Units | 16384 |
| 320 | Texture Mapping Units (TMUs) | 512 |
| 112 | Render Output Units (ROPs) | 176 |
| 80 | Compute Units (Pipelines) | 128 |
| 320 | Tensor Cores | 512 |
| 80 | Ray-tracing Cores | 128 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 6MB shared | L2 Cache | 72MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |