Quick/Comparisons
The GeForce RTX 4090's superior gaming performance is due to its higher CUDA core count and more advanced architecture. It delivers a 92/100 gaming score, leaving the GeForce RTX 4060 far behind.
The GeForce RTX 4090's strong workstation performance is driven by its high CUDA core count and ample memory, making it the clear winner in content creation tasks. It outperforms the GeForce RTX 4060 by a significant margin.
The GeForce RTX 4090's capable AI/ML compute capabilities are due to its dedicated tensor cores and higher CUDA core count, making it the better choice for AI and machine learning tasks. It outperforms the GeForce RTX 4060 by a notable margin.
35 | Gaming | 92 |
38 | Workstation | 91 |
32 | AI/ML | 76 |
63 | Energy Efficiency | 43 |
36 | Quick Comparison Final Score | 89 |
| AD107 | Graphics Processor | AD102 |
| 3072 | Cores | 16384 |
| 96 / 48 | TMUs / ROPs | 512 / 176 |
| 3125.73 | Blender GPU | 11688.48 |
| 80 | Forza Horizon 5 | 203 |
| 115 | The Witcher 3 | 270 |
| 155 | Counter-Strike 2 | 245 |
| 99 | Far Cry 6 | 183 |
| 64 | Hogwarts Legacy | 165 |
| 90 | Call of Duty | 269 |
| 61 | Ghost of Tsushima | 150 |
| 75 | Cyberpunk 2077 | 204 |
| 116 | Tomb Raider | 283 |
| 95 | Average FPS | 219 |
| 115 | 1080p High | 256 |
| 95 | 1080p Ultra | 219 |
| 69 | 1440p Ultra | 176 |
| 39 | 4K Ultra | 107 |
| Low | Margin of Error | Low |
| 106633 | GB6 Compute Score | 316301 |
| 186.9 img/sec | Background Blur | 318.9 img/sec |
| 112.7 img/sec | Face Detection | 222.8 img/sec |
| 3.92 Gpixels/sec | Horizon Detection | 14.2 Gpixels/sec |
| 5.16 Gpixels/sec | Edge Detection | 21 Gpixels/sec |
| 4.94 Gpixels/sec | Gaussian Blur | 23.9 Gpixels/sec |
| 1.34 Gpixels/sec | Feature Matching | 2.38 Gpixels/sec |
| 446.2 Gpixels/sec | Stereo Matching | 1950 Gpixels/sec |
| 14935.1 FPS | Particle Physics | 48090.4 FPS |
| OpenCL | API | OpenCL |
| 19523 | G3D Mark Score | 38071 |
| 1039 | G2D Mark | 1303 |
| 174 FPS | DirectX 11 | 324 FPS |
| 76 FPS | DirectX 12 | 151 FPS |
| 9185 Ops/s | GPU Compute | 26193 Ops/s |
| 17857 | GB6 ML Single Precision | 42962 |
| 29214 | GB6 ML Half Precision | 59636 |
| 14234 | GB6 ML Quantized | 31670 |
| 7696 | Image Classification (SP) | 15600 |
| 13706 | Image Segmentation (HP) | 36657 |
| 23289 | Image Super Resolution (Q) | 48114 |
| 31126 | Face Detection (HP) | 78111 |
| 78361 | Pose Estimation (Q) | 289639 |
| 3315 | Text Classification (SP) | 4074 |
| 3491 | Machine Translation (HP) | 6349 |
| 9386 | Object Detection (SP) | 21186 |
| 36778 | Depth Estimation (Q) | 75599 |
| 148120 | Style Transfer (SP) | 601428 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 118 GPixel/s | Pixel Fill Rate | 444 GPixel/s |
| 236 GTexel/s | Texture Fill Rate | 1290 GTexel/s |
| 15.1 TFLOPS | FLOPS (FP32) | 82.6 TFLOPS |
| GDDR6 | Memory Type | GDDR6X |
| 8 GB | Memory Size | 24 GB |
| — | Memory Clock | 2625 MHz |
| — | Effective Memory Speed | 21000 Mbps |
| 128-bit | Bus | 384-bit |
| No | ECC | No |
| 272 GB/s | Memory Bandwidth | 1010 GB/s |
| PCIe 4.0 x8 | Interface | PCIe 4.0 x16 |
| 115 W | TGP | 450 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 5 nm |
| 159 mm² | Die Size | 609 mm² |
| 18 billion | Transistor Count | 76.3 billion |
| 113.21 MTr/mm² | Transistor Density | 125.29 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.9 | CUDA | 8.9 |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | DLSS 3 |
| 1.4a | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| May 18, 2023 | Released | September 20, 2022 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Ada Lovelace | Architecture | Ada Lovelace |
| AD107 | GPU Codename | AD102 |
| -Intel Core i5 14600Kor above | Recommended CPU | -Intel Core i9 14900Kor above |
| 10683 | Steel Nomad Lite Score | 42169 |
| 10619 | Time Spy | 36311 |
| 49280 | Solar Bay | 187386 |
| 6054 | Port Royal | 26128 |
| 28548 | Fire Strike | 72387 |
| 20605 | Wild Life Extreme | 85230 |
| 121586 | Night Raid | 195880 |
| 1830 MHz | Base Clock | 2235 MHz |
| 2460 MHz | Boost Clock | 2520 MHz |
| 3072 | Shading Units | 16384 |
| 96 | Texture Mapping Units (TMUs) | 512 |
| 48 | Render Output Units (ROPs) | 176 |
| 24 | Compute Units (Pipelines) | 128 |
| 96 | Tensor Cores | 512 |
| 24 | Ray-tracing Cores | 128 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 24MB shared | L2 Cache | 72MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 4060 with another →