Quick/Comparisons
The GeForce RTX 4090's exceptional gaming performance, with a score of 92, makes it the clear winner in this category. Its 92 score is significantly higher than the Radeon RX 7800 XT's 56.
The GeForce RTX 4090's strong workstation performance, with a score of 91, gives it the edge in content creation tasks. Its 91 score is substantially higher than the Radeon RX 7800 XT's 55.
The GeForce RTX 4090's capable AI/ML compute, with a score of 76, makes it the winner in this category. Although the gap is not extreme, the GeForce RTX 4090's 76 score is higher than the Radeon RX 7800 XT's 54.
92 | Gaming | 56 |
91 | Workstation | 55 |
76 | AI/ML | 54 |
43 | Energy Efficiency | 45 |
89 | Quick Comparison Final Score | 55 |
| AD102 | Graphics Processor | Navi 32 |
| 16384 | Cores | 3840 |
| 512 / 176 | TMUs / ROPs | 240 / 96 |
| 11688.48 | Blender GPU | 2417.04 |
| 203 | Forza Horizon 5 | 136 |
| 270 | The Witcher 3 | 177 |
| 245 | Counter-Strike 2 | 205 |
| 183 | Far Cry 6 | 146 |
| 165 | Hogwarts Legacy | 102 |
| 269 | Call of Duty | 164 |
| 150 | Ghost of Tsushima | 102 |
| 204 | Cyberpunk 2077 | 122 |
| 283 | Tomb Raider | 193 |
| 219 | Average FPS | 150 |
| 256 | 1080p High | 181 |
| 219 | 1080p Ultra | 150 |
| 176 | 1440p Ultra | 114 |
| 107 | 4K Ultra | 67 |
| Low | Margin of Error | Low |
| 2.38 Gpixels/sec | Feature Matching | 1.25 Gpixels/sec |
| 1950 Gpixels/sec | Stereo Matching | 566.4 Gpixels/sec |
| 48090.4 FPS | Particle Physics | 20533.6 FPS |
| OpenCL | API | OpenCL |
| 316301 | GB6 Compute Score | 148335 |
| 318.9 img/sec | Background Blur | 300.7 img/sec |
| 222.8 img/sec | Face Detection | 200.5 img/sec |
| 14.2 Gpixels/sec | Horizon Detection | 5.77 Gpixels/sec |
| 21 Gpixels/sec | Edge Detection | 8.05 Gpixels/sec |
| 23.9 Gpixels/sec | Gaussian Blur | 6.44 Gpixels/sec |
| 38071 | G3D Mark Score | 24337 |
| 1303 | G2D Mark | 1191 |
| 324 FPS | DirectX 11 | 249 FPS |
| 151 FPS | DirectX 12 | 95 FPS |
| 26193 Ops/s | GPU Compute | 13568 Ops/s |
| 42962 | GB6 ML Single Precision | 31216 |
| 59636 | GB6 ML Half Precision | 37266 |
| 31670 | GB6 ML Quantized | 24564 |
| 15600 | Image Classification (SP) | 13913 |
| 36657 | Image Segmentation (HP) | 18416 |
| 48114 | Image Super Resolution (Q) | 31387 |
| 78111 | Face Detection (HP) | 51780 |
| 289639 | Pose Estimation (Q) | 177217 |
| 4074 | Text Classification (SP) | 3655 |
| 6349 | Machine Translation (HP) | 6216 |
| 21186 | Object Detection (SP) | 15073 |
| 75599 | Depth Estimation (Q) | 57318 |
| 601428 | Style Transfer (SP) | 347420 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 444 GPixel/s | Pixel Fill Rate | 233 GPixel/s |
| 1290 GTexel/s | Texture Fill Rate | 583 GTexel/s |
| 82.6 TFLOPS | FLOPS (FP32) | 37.3 TFLOPS |
| GDDR6X | Memory Type | GDDR6 |
| 24 GB | Memory Size | 16 GB |
| 2625 MHz | Memory Clock | 2438 MHz |
| 21000 Mbps | Effective Memory Speed | 19500 Mbps |
| 384-bit | Bus | 256-bit |
| No | ECC | No |
| 1010 GB/s | Memory Bandwidth | 624.1 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 450 W | TGP | 263 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 5 nm |
| 609 mm² | Die Size | 346 mm² |
| 76.3 billion | Transistor Count | 28 billion |
| 125.29 MTr/mm² | Transistor Density | 80.92 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.2 |
| 8.9 | CUDA | — |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Nvidia | Vendor | Amd |
| Discrete | Build | Discrete |
| September 20, 2022 | Released | September 6, 2023 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| Ada Lovelace | Architecture | RDNA 3.0 |
| AD102 | GPU Codename | Navi 32 |
| -Intel Core i9 14900Kor above | Recommended CPU | -Intel Core i5 13600Kor above |
| 42169 | Steel Nomad Lite Score | 18090 |
| 36311 | Time Spy | 20088 |
| 187386 | Solar Bay | 80288 |
| 26128 | Port Royal | 10921 |
| 72387 | Fire Strike | 50041 |
| 85230 | Wild Life Extreme | 37094 |
| 195880 | Night Raid | 160328 |
| 2235 MHz | Base Clock | 1295 MHz |
| 2520 MHz | Boost Clock | 2430 MHz |
| 16384 | Shading Units | 3840 |
| 512 | Texture Mapping Units (TMUs) | 240 |
| 176 | Render Output Units (ROPs) | 96 |
| 128 | Compute Units (Pipelines) | — |
| 512 | Tensor Cores | — |
| 128 | Ray-tracing Cores | 60 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 72MB shared | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 4 IPC |
Compare with something else?
Compare GeForce RTX 4090 with another →