Quick/Comparisons
21 | Gaming | 35 |
17 | Workstation | 41 |
12 | AI/ML |
Compare with something else?
Compare GeForce MX570 with another →34 |
75 | Energy Efficiency | 27 |
28 | Quick Comparison Final Score | 37 |
| GA107S | Graphics Processor | TU104 |
| 2048 | Cores | 2944 |
| 64 / 40 | TMUs / ROPs | 184 / 64 |
| 489.72 | Blender GPU | 2335.41 |
| — | Forza Horizon 5 | 81 |
| — | The Witcher 3 | 120 |
| — | Counter-Strike 2 | 160 |
| — | Far Cry 6 | 99 |
| — | Hogwarts Legacy | 65 |
| — | Call of Duty | 93 |
| — | Ghost of Tsushima | 62 |
| — | Cyberpunk 2077 | 75 |
| — | Tomb Raider | 123 |
| — | Average FPS | 98 |
| — | 1080p High | 119 |
| — | 1080p Ultra | 98 |
| — | 1440p Ultra | 72 |
| — | 4K Ultra | 40 |
| — | Margin of Error | Low |
| 42999 | GB6 Compute Score | 118637 |
| 77.2 img/sec | Background Blur | 191.8 img/sec |
| 40.3 img/sec | Face Detection | 115.9 img/sec |
| 1.65 Gpixels/sec | Horizon Detection | 4.74 Gpixels/sec |
| 2.13 Gpixels/sec | Edge Detection | 6.2 Gpixels/sec |
| 2.04 Gpixels/sec | Gaussian Blur | 6.56 Gpixels/sec |
| 0.57 Gpixels/sec | Feature Matching | 1.3 Gpixels/sec |
| 181.5 Gpixels/sec | Stereo Matching | 499.7 Gpixels/sec |
| 5728.6 FPS | Particle Physics | 15858.8 FPS |
| OpenCL | API | OpenCL |
| 5795 | G3D Mark Score | 18607 |
| 388 | G2D Mark | 900 |
| 38 FPS | DirectX 11 | 159 FPS |
| 30 FPS | DirectX 12 | 71 FPS |
| 2561 Ops/s | GPU Compute | 7761 Ops/s |
| 5997 | GB6 ML Single Precision | 17223 |
| 11591 | GB6 ML Half Precision | 28694 |
| 4316 | GB6 ML Quantized | 11608 |
| 2792 | Image Classification (SP) | 7122 |
| 5831 | Image Segmentation (HP) | 17897 |
| 5115 | Image Super Resolution (Q) | 16120 |
| 9491 | Face Detection (HP) | 34245 |
| 19218 | Pose Estimation (Q) | 69601 |
| 1996 | Text Classification (SP) | 2181 |
| 1992 | Machine Translation (HP) | 4328 |
| 2848 | Object Detection (SP) | 8748 |
| 10712 | Depth Estimation (Q) | 28373 |
| 44344 | Style Transfer (SP) | 154510 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 59 GPixel/s | Pixel Fill Rate | 109 GPixel/s |
| 95 GTexel/s | Texture Fill Rate | 315 GTexel/s |
| 6 TFLOPS | FLOPS (FP32) | 10.1 TFLOPS |
| GDDR6 | Memory Type | GDDR6 |
| 4 GB | Memory Size | 8 GB |
| 1500 MHz | Memory Clock | 1750 MHz |
| 12000 Mbps | Effective Memory Speed | 14000 Mbps |
| 64-bit | Bus | 256-bit |
| — | ECC | No |
| 96 GB/s | Memory Bandwidth | 448 GB/s |
| PCIe 4.0 x8 | Interface | PCIe 3.0 x16 |
| 45 W | TGP | 215 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 12 nm |
| 200 mm² | Die Size | 545 mm² |
| 8.7 billion | Transistor Count | 13 billion |
| 43.5 MTr/mm² | Transistor Density | 23.85 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.6 | CUDA | 7.5 |
| Yes | Ray Tracing | Yes |
| No | DLSS | DLSS 2 |
| 1.4 | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 1, 2022 | Released | September 20, 2018 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Entry-level | Segment | High-end |
| Ampere | Architecture | Turing |
| GA107S | GPU Codename | TU104 |
| -Intel Core i7 1255Uor above | Recommended CPU | -AMD Ryzen 9 9900Xor above |
| — | Steel Nomad Lite Score | 10886 |
| — | Time Spy | 11079 |
| — | Solar Bay | 49857 |
| — | Port Royal | 6459 |
| — | Fire Strike | 27671 |
| — | Wild Life Extreme | 22290 |
| — | Night Raid | 100751 |
| 1155 MHz | Base Clock | 1515 MHz |
| 1477 MHz | Boost Clock | 1710 MHz |
| 2048 | Shading Units | 2944 |
| 64 | Texture Mapping Units (TMUs) | 184 |
| 40 | Render Output Units (ROPs) | 64 |
| 16 | Compute Units (Pipelines) | 46 |
| 64 | Tensor Cores | 368 |
| 16 | Ray-tracing Cores | 46 |
| 128KB per cluster | L1 Cache | 64KB per cluster |
| 2MB shared | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |