Quick/Comparisons
6 | Gaming | 80 |
14 | Workstation | 71 |
7 | AI/ML |
Compare with something else?
Compare GeForce MX450 with another →66 |
71 | Energy Efficiency | 43 |
19 | Quick Comparison Final Score | 75 |
| TU117 | Graphics Processor | AD103 |
| 896 | Cores | 9728 |
| 56 / 32 | TMUs / ROPs | 304 / 112 |
| 201.01 | Blender GPU | 8710.73 |
| 10 | Forza Horizon 5 | — |
| 12 | The Witcher 3 | — |
| 22 | Counter-Strike 2 | — |
| 21 | Far Cry 6 | — |
| 10 | Hogwarts Legacy | — |
| 23 | Call of Duty | — |
| - | Ghost of Tsushima | — |
| - | Cyberpunk 2077 | — |
| 17 | Tomb Raider | — |
| 14 | Average FPS | — |
| 20 | 1080p High | — |
| 14 | 1080p Ultra | — |
| 10 | 1440p Ultra | — |
| - | 4K Ultra | — |
| Medium | Margin of Error | — |
| 34221 | GB6 Compute Score | 217712 |
| 65.7 img/sec | Background Blur | 250.4 img/sec |
| 33.3 img/sec | Face Detection | 190 img/sec |
| 1.01 Gpixels/sec | Horizon Detection | 9.56 Gpixels/sec |
| 1.39 Gpixels/sec | Edge Detection | 12.8 Gpixels/sec |
| 1.61 Gpixels/sec | Gaussian Blur | 15.3 Gpixels/sec |
| 0.48 Gpixels/sec | Feature Matching | 1.97 Gpixels/sec |
| 176 Gpixels/sec | Stereo Matching | 1130 Gpixels/sec |
| 5012.4 FPS | Particle Physics | 28795.5 FPS |
| OpenCL | API | OpenCL |
| 3718 | G3D Mark Score | 34430 |
| 305 | G2D Mark | 1250 |
| 26 FPS | DirectX 11 | 313 FPS |
| 23 FPS | DirectX 12 | 132 FPS |
| 1867 Ops/s | GPU Compute | 20406 Ops/s |
| 4394 | GB6 ML Single Precision | 36799 |
| 4387 | GB6 ML Half Precision | 53331 |
| 3246 | GB6 ML Quantized | 28104 |
| 1911 | Image Classification (SP) | 13466 |
| 2536 | Image Segmentation (HP) | 34767 |
| 4111 | Image Super Resolution (Q) | 42687 |
| 5175 | Face Detection (HP) | 70927 |
| 13374 | Pose Estimation (Q) | 239350 |
| 1514 | Text Classification (SP) | 3606 |
| 1481 | Machine Translation (HP) | 6519 |
| 2070 | Object Detection (SP) | 18153 |
| 7813 | Depth Estimation (Q) | 65667 |
| 36156 | Style Transfer (SP) | 414848 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 30-50 GPixel/s | Pixel Fill Rate | 281 GPixel/s |
| 52-88 GTexel/s | Texture Fill Rate | 762 GTexel/s |
| 1.7-2.8 TFLOPS | FLOPS (FP32) | 48.7 TFLOPS |
| 10000 Mbps | Effective Memory Speed | 22400 Mbps |
| 64-bit | Bus | 256-bit |
| — | ECC | No |
| 80 GB/s | Memory Bandwidth | 716.8 GB/s |
| GDDR6 | Memory Type | GDDR6X |
| 2 GB | Memory Size | 16 GB |
| 1250 MHz | Memory Clock | 1400 MHz |
| PCIe 4.0 x4 | Interface | PCIe 4.0 x16 |
| 10-30 W (configurable) | TGP | 320 W |
| TSMC | Manufacturing | TSMC |
| 12 nm | Fabrication Process | 5 nm |
| 200 mm² | Die Size | 379 mm² |
| 4.7 billion | Transistor Count | 45 billion |
| 23.5 MTr/mm² | Transistor Density | 118.73 MTr/mm² |
| 12 | DirectX | 12 |
| 1.2 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 1.2 | OpenCL | 3 |
| 7.5 | CUDA | 8.9 |
| No | Ray Tracing | Yes |
| No | DLSS | DLSS 3 |
| 1.4 | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| August 25, 2020 | Released | September 20, 2022 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Turing | Architecture | Ada Lovelace |
| TU117 | GPU Codename | AD103 |
| -Intel Core i5 11300Hor above | Recommended CPU | -Intel Core i7 14700Kor above |
| 1174 | Steel Nomad Lite Score | 30172 |
| 2118 | Time Spy | 28161 |
| — | Solar Bay | 136931 |
| — | Port Royal | 17982 |
| 5267 | Fire Strike | 64633 |
| 4259 | Wild Life Extreme | 59111 |
| 26243 | Night Raid | 184963 |
| 720-1395 MHz (configurable) | Base Clock | 2205 MHz |
| 930-1575 MHz (configurable) | Boost Clock | 2505 MHz |
| 896 | Shading Units | 9728 |
| 56 | Texture Mapping Units (TMUs) | 304 |
| 32 | Render Output Units (ROPs) | 112 |
| 14 | Compute Units (Pipelines) | 76 |
| No | Tensor Cores | 304 |
| No | Ray-tracing Cores | 76 |
| 64KB per cluster | L1 Cache | 128KB per cluster |
| 512KB shared | L2 Cache | 64MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |