Quick/Comparisons
9 | Gaming | 50 |
8 | Workstation | 59 |
| — | AI/ML |
Compare with something else?
Compare Adreno X1-45 with another →93 | Energy Efficiency | 61 |
24 | Quick Comparison Final Score | 52 |
| Adreno X1 | Graphics Processor | Custom |
| 768 | Cores | 10240 |
| 48 / 24 | TMUs / ROPs | 640 / 320 |
| — | Blender GPU | 7360.18 |
| — | Forza Horizon 5 | — |
| — | The Witcher 3 | — |
| — | Counter-Strike 2 | — |
| — | Far Cry 6 | — |
| — | Hogwarts Legacy | — |
| — | Call of Duty | — |
| — | Ghost of Tsushima | — |
| — | Cyberpunk 2077 | — |
| — | Tomb Raider | — |
| — | Average FPS | — |
| — | 1080p High | — |
| — | 1080p Ultra | — |
| — | 1440p Ultra | — |
| — | 4K Ultra | — |
| — | Margin of Error | — |
| 9947 | GB6 Compute Score | 147719 |
| 14.2 img/sec | Background Blur | 204.5 img/sec |
| 6.82 img/sec | Face Detection | 126 img/sec |
| 0.56 Gpixels/sec | Horizon Detection | 6.53 Gpixels/sec |
| 0.65 Gpixels/sec | Edge Detection | 10.7 Gpixels/sec |
| 0.55 Gpixels/sec | Gaussian Blur | 9.5 Gpixels/sec |
| 0.12 Gpixels/sec | Feature Matching | 1.05 Gpixels/sec |
| 26.6 Gpixels/sec | Stereo Matching | 560.3 Gpixels/sec |
| 1746.7 FPS | Particle Physics | 25267.8 FPS |
| OpenCL | API | OpenCL |
| 1893 | G3D Mark Score | — |
| 357 | G2D Mark | — |
| 13 FPS | DirectX 11 | — |
| 9 FPS | DirectX 12 | — |
| 818 Ops/s | GPU Compute | — |
| — | GB6 ML Single Precision | 21356 |
| — | GB6 ML Half Precision | 23530 |
| — | GB6 ML Quantized | 21706 |
| — | Image Classification (SP) | 8094 |
| — | Image Segmentation (HP) | 24595 |
| — | Image Super Resolution (Q) | 25190 |
| — | Face Detection (HP) | 38337 |
| — | Pose Estimation (Q) | 111021 |
| — | Text Classification (SP) | 2786 |
| — | Machine Translation (HP) | 4339 |
| — | Object Detection (SP) | 7668 |
| — | Depth Estimation (Q) | 37488 |
| — | Style Transfer (SP) | 244483 |
| — | Framework | Core ML |
| — | Backend | GPU |
| 27-33 GPixel/s | Pixel Fill Rate | 442 GPixel/s |
| 53-66 GTexel/s | Texture Fill Rate | 883 GTexel/s |
| 1.7-2.1 TFLOPS | FLOPS (FP32) | 28.3 TFLOPS |
| System Shared | Memory Type | System Shared |
| — | Memory Size | — |
| — | Memory Clock | 6400 MHz |
| — | Effective Memory Speed | — |
| — | Bus | 1024-bit |
| — | ECC | No |
| — | Memory Bandwidth | 819.3 GB/s |
| IGP | Interface | Custom |
| — | TGP | 140 W |
| TSMC | Manufacturing | TSMC |
| 4 nm | Fabrication Process | 3 nm |
| — | Die Size | — |
| — | Transistor Count | 184 billion |
| — | Transistor Density | — |
| 12.1 | DirectX | — |
| 1.3 | Vulkan | — |
| 3.2 | OpenGL | — |
| 3 | OpenCL | — |
| No | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| 1.4 | DisplayPort | — |
| Qualcomm | Vendor | Apple |
| Integrated | Build | Integrated |
| October 24, 2023 | Released | March 5, 2025 |
| Laptop | Case | Desktop |
| Generic | Purpose | Professional |
| Entry-level | Segment | High-end |
| Adreno X1 | Architecture | Apple M GPU |
| Adreno X1 | GPU Codename | Custom |
| -Qualcomm Snapdragon X (X1-26-100)or above | Recommended CPU | -Apple M3 Ultraor above |
| 1084 | Steel Nomad Lite Score | 19491 |
| 928 | Time Spy | — |
| 5988 | Solar Bay | 73690 |
| — | Port Royal | — |
| 3706 | Fire Strike | — |
| 3224 | Wild Life Extreme | 44759 |
| 16550 | Night Raid | — |
| 280 MHz | Base Clock | — |
| 1107-1367 MHz (configurable) | Boost Clock | 1380 MHz |
| 768 | Shading Units | 10240 |
| 48 | Texture Mapping Units (TMUs) | 640 |
| 24 | Render Output Units (ROPs) | 320 |
| 3 | Compute Units (Pipelines) | 1280 |
| — | Tensor Cores | — |
| — | Ray-tracing Cores | — |
| 192KB per cluster | L1 Cache | — |
| 1MB shared | L2 Cache | — |
| 2 IPC | Instructions Per Cycle | 2 IPC |