Quick/Comparisons
The GeForce RTX 4080 SUPER's superior gaming performance, with a score of 78, far surpasses the GeForce RTX 3050 Laptop's score of 18.
Both the GeForce RTX 3050 Laptop and GeForce RTX 4080 SUPER have strong workstation capabilities, with scores of 25 and 76 respectively, making them essentially tied.
The GeForce RTX 4080 SUPER's AI/ML score of 66 edges out the GeForce RTX 3050 Laptop's score of 18, indicating its superiority in this area.
25 | Workstation | 76 |
18 | AI/ML | 66 |
59 | Energy Efficiency | 46 |
27 | Quick Comparison Final Score | 75 |
18 | Gaming | 78 |
| GA107 | Graphics Processor | AD103 |
| 2048 | Cores | 10240 |
| 64 / 40 | TMUs / ROPs | 320 / 112 |
| 1162.84 | Blender GPU | 8420.48 |
| 44 | Forza Horizon 5 | 171 |
| 55 | The Witcher 3 | 210 |
| 80 | Counter-Strike 2 | 223 |
| 53 | Far Cry 6 | 166 |
| 27 | Hogwarts Legacy | 137 |
| 39 | Call of Duty | 216 |
| 24 | Ghost of Tsushima | 122 |
| 34 | Cyberpunk 2077 | 177 |
| 59 | Tomb Raider | 265 |
| 46 | Average FPS | 187 |
| 60 | 1080p High | 221 |
| 46 | 1080p Ultra | 187 |
| 32 | 1440p Ultra | 149 |
| 17 | 4K Ultra | 87 |
| Low | Margin of Error | Low |
| 58733 | GB6 Compute Score | 250691 |
| 88.6 img/sec | Background Blur | 279.5 img/sec |
| 57.3 img/sec | Face Detection | 220.1 img/sec |
| 2.53 Gpixels/sec | Horizon Detection | 11 Gpixels/sec |
| 3.33 Gpixels/sec | Edge Detection | 15.2 Gpixels/sec |
| 2.55 Gpixels/sec | Gaussian Blur | 16.2 Gpixels/sec |
| 0.76 Gpixels/sec | Feature Matching | 2.08 Gpixels/sec |
| 256.5 Gpixels/sec | Stereo Matching | 1370 Gpixels/sec |
| 7465.5 FPS | Particle Physics | 37199.7 FPS |
| OpenCL | API | OpenCL |
| 9493 | G3D Mark Score | 34252 |
| 490 | G2D Mark | 1278 |
| 71 FPS | DirectX 11 | 300 FPS |
| 46 FPS | DirectX 12 | 134 FPS |
| 3860 Ops/s | GPU Compute | 19639 Ops/s |
| 10038 | GB6 ML Single Precision | 36883 |
| 19152 | GB6 ML Half Precision | 54286 |
| 6984 | GB6 ML Quantized | 28474 |
| 4349 | Image Classification (SP) | 12453 |
| 11416 | Image Segmentation (HP) | 34467 |
| 8973 | Image Super Resolution (Q) | 43534 |
| 18927 | Face Detection (HP) | 70300 |
| 34631 | Pose Estimation (Q) | 242331 |
| 2269 | Text Classification (SP) | 3767 |
| 3539 | Machine Translation (HP) | 6614 |
| 5046 | Object Detection (SP) | 18301 |
| 15772 | Depth Estimation (Q) | 66477 |
| 75260 | Style Transfer (SP) | 417906 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 42-70 GPixel/s | Pixel Fill Rate | 286 GPixel/s |
| 68-111 GTexel/s | Texture Fill Rate | 816 GTexel/s |
| 4.3-7.1 TFLOPS | FLOPS (FP32) | 52.2 TFLOPS |
| GDDR6 | Memory Type | GDDR6X |
| 4 GB | Memory Size | 16 GB |
| 1500 MHz | Memory Clock | 1438 MHz |
| 12000 Mbps | Effective Memory Speed | 23000 Mbps |
| 128-bit | Bus | 256-bit |
| No | ECC | No |
| 192 GB/s | Memory Bandwidth | 736.3 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 35-95 W (configurable) | TGP | 320 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 5 nm |
| 200 mm² | Die Size | 379 mm² |
| 8.7 billion | Transistor Count | 45 billion |
| 43.5 MTr/mm² | Transistor Density | 118.73 MTr/mm² |
| 12 | DirectX | 12 |
| 1.2 | 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 1, 2021 | Released | January 31, 2024 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Ampere | Architecture | Ada Lovelace |
| GA107 | GPU Codename | AD103 |
| — | Recommended CPU | -Intel Core i7 14700Kor above |
| 4914 | Steel Nomad Lite Score | 30711 |
| 4884 | Time Spy | 28279 |
| 21603 | Solar Bay | 138998 |
| 552 | Port Royal | 18348 |
| 12561 | Fire Strike | 63714 |
| 9421 | Wild Life Extreme | 60015 |
| 53654 | Night Raid | 180412 |
| 712-1530 MHz (configurable) | Base Clock | 2295 MHz |
| 1057-1740 MHz (configurable) | Boost Clock | 2550 MHz |
| 2048 | Shading Units | 10240 |
| 64 | Texture Mapping Units (TMUs) | 320 |
| 40 | Render Output Units (ROPs) | 112 |
| 16 | Compute Units (Pipelines) | 80 |
| 64 | Tensor Cores | 320 |
| 16 | Ray-tracing Cores | 80 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 2MB shared | L2 Cache | 64MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 3050 with another →