Quick/Comparisons
A entry-level Nvidia GeForce RTX 3080 Ti Laptop graphics card with modest workstation performance (48/100). Suited for casual gaming and basic graphics tasks.
| Gaming | 42 /100 |
| Workstation | 48 /100 |
| AI/ML | 37 /100 |
| Energy Efficiency | 37 |
Looking for more comparisons?
Compare GeForce RTX →| Quick Comparison Final Score | 42 /100 |
| Graphics Processor | GA103 (GN20-E8) |
| Cores | 7424 |
| TMUs / ROPs | 232 / 96 |
| Blender GPU | 3502.46 |
| Forza Horizon 5 | 92 |
| The Witcher 3 | 136 |
| Counter-Strike 2 | 181 |
| Far Cry 6 | 111 |
| Hogwarts Legacy | 79 |
| Call of Duty | 106 |
| Ghost of Tsushima | 72 |
| Cyberpunk 2077 | 86 |
| Tomb Raider | 143 |
| Average FPS | 112 |
| 1080p High | 135 |
| 1080p Ultra | 112 |
| 1440p Ultra | 83 |
| 4K Ultra | 47 |
| Margin of Error | Low |
| GB6 Compute Score | 133659 |
| Background Blur | 200.9 img/sec |
| Face Detection | 131.2 img/sec |
| Horizon Detection | 6.49 Gpixels/sec |
| Edge Detection | 8.9 Gpixels/sec |
| Gaussian Blur | 6.34 Gpixels/sec |
| Feature Matching | 1.2 Gpixels/sec |
| Stereo Matching | 571 Gpixels/sec |
| Particle Physics | 17240.3 FPS |
| API | OpenCL |
| G3D Mark Score | 18948 |
| G2D Mark | 817 |
| DirectX 11 | 161 FPS |
| DirectX 12 | 87 FPS |
| GPU Compute | 8302 Ops/s |
| GB6 ML Single Precision | 18415 |
| GB6 ML Half Precision | 29828 |
| GB6 ML Quantized | 11425 |
| Image Classification (SP) | 6797 |
| Image Segmentation (HP) | 20808 |
| Image Super Resolution (Q) | 15194 |
| Face Detection (HP) | 37084 |
| Pose Estimation (Q) | 82268 |
| Text Classification (SP) | 2863 |
| Machine Translation (HP) | 4135 |
| Object Detection (SP) | 8559 |
| Depth Estimation (Q) | 28330 |
| Style Transfer (SP) | 184129 |
| Framework | ONNX |
| Backend | DirectML |
| Pixel Fill Rate | 108-153 GPixel/s |
| Texture Fill Rate | 261-369 GTexel/s |
| FLOPS (FP32) | 16.7-23.6 TFLOPS |
| Memory Type | GDDR6 |
| Memory Size | 16 GB |
| Memory Clock | 2000 MHz |
| Effective Memory Speed | 16000 Mbps |
| Bus | 256-bit |
| ECC | No |
| Memory Bandwidth | 512 GB/s |
| Interface | PCIe 4.0 x16 |
| TGP | 80-175 W (configurable) |
| Manufacturing | Samsung |
| Fabrication Process | 8 nm |
| Die Size | 496 mm² |
| Transistor Count | 22 billion |
| Transistor Density | 44.35 MTr/mm² |
| DirectX | 12 |
| Vulkan | 1.2 |
| OpenGL | 4.6 |
| OpenCL | 3 |
| CUDA | 8.6 |
| Ray Tracing | Yes |
| DLSS | DLSS 2 |
| DisplayPort | 1.4a |
| Vendor | Nvidia |
| Build | Discrete |
| Released | January 1, 2022 |
| Case | Laptop |
| Purpose | Gaming |
| Segment | High-end |
| Architecture | Ampere |
| GPU Codename | GA103 (GN20-E8) |
| Recommended CPU | -Intel Core i9 12900Hor above |
| Steel Nomad Lite Score | 12913 |
| Time Spy | 12864 |
| Solar Bay | 56305 |
| Port Royal | 8092 |
| Fire Strike | 30858 |
| Wild Life Extreme | 26307 |
| Night Raid | 98582 |
| Base Clock | 585-1230 MHz (configurable) |
| Boost Clock | 1125-1590 MHz (configurable) |
| Shading Units | 7424 |
| Texture Mapping Units (TMUs) | 232 |
| Render Output Units (ROPs) | 96 |
| Compute Units (Pipelines) | 58 |
| Tensor Cores | 232 |
| Ray-tracing Cores | 58 |
| L1 Cache | 128KB per cluster |
| L2 Cache | 4MB shared |
| Instructions Per Cycle | 2 IPC |
GeForce RTX 5080
84/100