Quick/Comparisons
The GeForce RTX 3080's superior gaming performance is evident, with a score 46 points higher than the GeForce MX230. Its advanced features like hardware ray tracing support contribute to its lead.
The GeForce RTX 3080 takes the lead in content creation, with a score 48 points higher than the GeForce MX230. Its higher workstation score and support for advanced features like DLSS upscaling support make it the better choice.
The GeForce RTX 3080 outperforms the GeForce MX230 in AI & Machine Learning, with a score 40 points higher. Its dedicated AI tensor cores and higher AI/ML score contribute to its lead.
9 | Gaming | 55 |
8 | Workstation | 56 |
3 | AI/ML |
Compare with something else?
Compare GeForce MX230 with another →43 |
73 | Energy Efficiency | 35 |
19 | Quick Comparison Final Score | 54 |
| GP108 | Graphics Processor | GA102 |
| 256 | Cores | 8704 |
| 16 / 16 | TMUs / ROPs | 272 / 96 |
| 41.33 | Blender GPU | 4812.92 |
| — | Forza Horizon 5 | 114 |
| — | The Witcher 3 | 163 |
| — | Counter-Strike 2 | 205 |
| — | Far Cry 6 | 137 |
| — | Hogwarts Legacy | 97 |
| — | Call of Duty | 146 |
| — | Ghost of Tsushima | 90 |
| — | Cyberpunk 2077 | 121 |
| — | Tomb Raider | 193 |
| — | Average FPS | 141 |
| — | 1080p High | 167 |
| — | 1080p Ultra | 141 |
| — | 1440p Ultra | 109 |
| — | 4K Ultra | 63 |
| — | Margin of Error | Low |
| 7785 | GB6 Compute Score | 161903 |
| 19.4 img/sec | Background Blur | 217.3 img/sec |
| 9.09 img/sec | Face Detection | 141.9 img/sec |
| 0.29 Gpixels/sec | Horizon Detection | 8.19 Gpixels/sec |
| 0.43 Gpixels/sec | Edge Detection | 11 Gpixels/sec |
| 0.44 Gpixels/sec | Gaussian Blur | 8.43 Gpixels/sec |
| 0.08 Gpixels/sec | Feature Matching | 1.29 Gpixels/sec |
| 25 Gpixels/sec | Stereo Matching | 780.7 Gpixels/sec |
| 759.2 FPS | Particle Physics | 22538.5 FPS |
| OpenCL | API | OpenCL |
| 1818 | G3D Mark Score | 25030 |
| 213 | G2D Mark | 1062 |
| 15 FPS | DirectX 11 | 207 FPS |
| 9 FPS | DirectX 12 | 100 FPS |
| 762 Ops/s | GPU Compute | 14154 Ops/s |
| 1408 | GB6 ML Single Precision | 24003 |
| 1384 | GB6 ML Half Precision | 36895 |
| 1028 | GB6 ML Quantized | 14629 |
| 277 | Image Classification (SP) | 9439 |
| 726 | Image Segmentation (HP) | 25471 |
| 1787 | Image Super Resolution (Q) | 19892 |
| 1076 | Face Detection (HP) | 46956 |
| 5990 | Pose Estimation (Q) | 104704 |
| 743 | Text Classification (SP) | 2712 |
| 970 | Machine Translation (HP) | 4828 |
| 379 | Object Detection (SP) | 12153 |
| 2059 | Depth Estimation (Q) | 36822 |
| 11915 | Style Transfer (SP) | 246005 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 24 GPixel/s | Pixel Fill Rate | 164 GPixel/s |
| 24 GTexel/s | Texture Fill Rate | 465 GTexel/s |
| 0.8 TFLOPS | FLOPS (FP32) | 29.8 TFLOPS |
| GDDR5 | Memory Type | GDDR6X |
| 2 GB | Memory Size | 10 GB |
| 1502 MHz | Memory Clock | 1188 MHz |
| 6000 Mbps | Effective Memory Speed | 19000 Mbps |
| 64-bit | Bus | 320-bit |
| — | ECC | No |
| 48 GB/s | Memory Bandwidth | 760.3 GB/s |
| PCIe 3.0 x4 | Interface | PCIe 4.0 x16 |
| 10 W | TGP | 320 W |
| Samsung | Manufacturing | Samsung |
| 14 nm | Fabrication Process | 8 nm |
| 74 mm² | Die Size | 628 mm² |
| 1.8 billion | Transistor Count | 28 billion |
| 24.32 MTr/mm² | Transistor Density | 44.59 MTr/mm² |
| 12 | DirectX | 12 |
| 1.2 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 1.2 | OpenCL | 3 |
| 6.1 | CUDA | 8.6 |
| No | Ray Tracing | Yes |
| No | DLSS | DLSS 2 |
| 1.4 | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| February 21, 2019 | Released | September 1, 2020 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Entry-level | Segment | High-end |
| Pascal | Architecture | Ampere |
| GP108 | GPU Codename | GA102 |
| -Intel Core i7 1065G7or above | Recommended CPU | -Intel Core i7 12700Kor above |
| — | Steel Nomad Lite Score | 19046 |
| — | Time Spy | 17664 |
| — | Solar Bay | 85890 |
| — | Port Royal | 11597 |
| — | Fire Strike | 42468 |
| — | Wild Life Extreme | 37899 |
| — | Night Raid | 132892 |
| 1519 MHz | Base Clock | 1440 MHz |
| 1531 MHz | Boost Clock | 1710 MHz |
| 256 | Shading Units | 8704 |
| 16 | Texture Mapping Units (TMUs) | 272 |
| 16 | Render Output Units (ROPs) | 96 |
| 2 | Compute Units (Pipelines) | 68 |
| No | Tensor Cores | 272 |
| No | Ray-tracing Cores | 68 |
| 48KB per cluster | L1 Cache | 128KB per cluster |
| 512KB shared | L2 Cache | 5MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |