Quick/Comparisons
The GeForce RTX 4090's 92 score in gaming performance far surpasses the Radeon RX 6750 XT's 39, making it the clear winner for gaming needs.
The GeForce RTX 4090's strong workstation performance, with a score of 91, outshines the Radeon RX 6750 XT's 42, making it the better choice for content creation.
The GeForce RTX 4090's capable AI/ML compute, with a score of 76, edges out the Radeon RX 6750 XT's 39, making it the winner for AI and machine learning tasks.
92 | Gaming | 39 |
91 | Workstation | 42 |
76 | AI/ML | 39 |
43 | Energy Efficiency | 38 |
89 | Quick Comparison Final Score | 40 |
| AD102 | Graphics Processor | Navi 22 |
| 16384 | Cores | 2560 |
| 512 / 176 | TMUs / ROPs | 160 / 64 |
| 11688.48 | Blender GPU | 1614.27 |
| 203 | Forza Horizon 5 | 96 |
| 270 | The Witcher 3 | 130 |
| 245 | Counter-Strike 2 | 162 |
| 183 | Far Cry 6 | 109 |
| 165 | Hogwarts Legacy | 76 |
| 269 | Call of Duty | 116 |
| 150 | Ghost of Tsushima | 79 |
| 204 | Cyberpunk 2077 | 85 |
| 283 | Tomb Raider | 142 |
| 219 | Average FPS | 111 |
| 256 | 1080p High | 138 |
| 219 | 1080p Ultra | 111 |
| 176 | 1440p Ultra | 81 |
| 107 | 4K Ultra | 45 |
| Low | Margin of Error | Low |
| 2.38 Gpixels/sec | Feature Matching | 1.05 Gpixels/sec |
| 1950 Gpixels/sec | Stereo Matching | 486.3 Gpixels/sec |
| 48090.4 FPS | Particle Physics | 14431.3 FPS |
| OpenCL | API | OpenCL |
| 316301 | GB6 Compute Score | 111003 |
| 318.9 img/sec | Background Blur | 229.3 img/sec |
| 222.8 img/sec | Face Detection | 155.2 img/sec |
| 14.2 Gpixels/sec | Horizon Detection | 3.72 Gpixels/sec |
| 21 Gpixels/sec | Edge Detection | 5.9 Gpixels/sec |
| 23.9 Gpixels/sec | Gaussian Blur | 4.51 Gpixels/sec |
| 38071 | G3D Mark Score | 20714 |
| 1303 | G2D Mark | 980 |
| 324 FPS | DirectX 11 | 180 FPS |
| 151 FPS | DirectX 12 | 81 FPS |
| 26193 Ops/s | GPU Compute | 9526 Ops/s |
| 42962 | GB6 ML Single Precision | 22788 |
| 59636 | GB6 ML Half Precision | 25354 |
| 31670 | GB6 ML Quantized | 17573 |
| 15600 | Image Classification (SP) | 10407 |
| 36657 | Image Segmentation (HP) | 11932 |
| 48114 | Image Super Resolution (Q) | 26548 |
| 78111 | Face Detection (HP) | 34995 |
| 289639 | Pose Estimation (Q) | 101235 |
| 4074 | Text Classification (SP) | 2618 |
| 6349 | Machine Translation (HP) | 5369 |
| 21186 | Object Detection (SP) | 10991 |
| 75599 | Depth Estimation (Q) | 40264 |
| 601428 | Style Transfer (SP) | 207126 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 444 GPixel/s | Pixel Fill Rate | 166 GPixel/s |
| 1290 GTexel/s | Texture Fill Rate | 416 GTexel/s |
| 82.6 TFLOPS | FLOPS (FP32) | 13.3 TFLOPS |
| GDDR6X | Memory Type | GDDR6 |
| 24 GB | Memory Size | 12 GB |
| 2625 MHz | Memory Clock | 2250 MHz |
| 21000 Mbps | Effective Memory Speed | 18000 Mbps |
| 384-bit | Bus | 192-bit |
| No | ECC | No |
| 1010 GB/s | Memory Bandwidth | 432 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 450 W | TGP | 250 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 7 nm |
| 609 mm² | Die Size | 335 mm² |
| 76.3 billion | Transistor Count | 17 billion |
| 125.29 MTr/mm² | Transistor Density | 50.75 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.1 |
| 8.9 | CUDA | — |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | No |
| 1.4a | DisplayPort | 1.4a |
| Nvidia | Vendor | Amd |
| Discrete | Build | Discrete |
| September 20, 2022 | Released | March 3, 2022 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| Ada Lovelace | Architecture | RDNA 2.0 |
| AD102 | GPU Codename | Navi 22 |
| -Intel Core i9 14900Kor above | Recommended CPU | -Intel Core i7 12700Kor above |
| 42169 | Steel Nomad Lite Score | 12088 |
| 36311 | Time Spy | 13555 |
| 187386 | Solar Bay | 52889 |
| 26128 | Port Royal | 6680 |
| 72387 | Fire Strike | 37723 |
| 85230 | Wild Life Extreme | 24124 |
| 195880 | Night Raid | 134131 |
| 2235 MHz | Base Clock | 2150 MHz |
| 2520 MHz | Boost Clock | 2600 MHz |
| 16384 | Shading Units | 2560 |
| 512 | Texture Mapping Units (TMUs) | 160 |
| 176 | Render Output Units (ROPs) | 64 |
| 128 | Compute Units (Pipelines) | — |
| 512 | Tensor Cores | — |
| 128 | Ray-tracing Cores | 40 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 72MB shared | L2 Cache | 3MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 4090 with another →