Quick/Comparisons
23 | Gaming | 22 |
29 | Workstation | 17 |
22 | AI/ML |
Compare with something else?
Compare GeForce RTX 3050 with another →| — |
50 | Energy Efficiency | 66 |
25 | Quick Comparison Final Score | 28 |
| GA106 | Graphics Processor | Strix Halo |
| 2560 | Cores | 1024 |
| 80 / 32 | TMUs / ROPs | 64 / 32 |
| 1475.37 | Blender GPU | 376.14 |
| 52 | Forza Horizon 5 | — |
| 71 | The Witcher 3 | — |
| 99 | Counter-Strike 2 | — |
| 68 | Far Cry 6 | — |
| 37 | Hogwarts Legacy | — |
| 52 | Call of Duty | — |
| 35 | Ghost of Tsushima | — |
| 42 | Cyberpunk 2077 | — |
| 76 | Tomb Raider | — |
| 59 | Average FPS | — |
| 75 | 1080p High | — |
| 59 | 1080p Ultra | — |
| 43 | 1440p Ultra | — |
| 23 | 4K Ultra | — |
| Low | Margin of Error | — |
| 67028 | GB6 Compute Score | 35976 |
| 110.4 img/sec | Background Blur | 106.8 img/sec |
| 64.4 img/sec | Face Detection | 43.8 img/sec |
| 2.87 Gpixels/sec | Horizon Detection | 1.12 Gpixels/sec |
| 3.76 Gpixels/sec | Edge Detection | 1.17 Gpixels/sec |
| 2.89 Gpixels/sec | Gaussian Blur | 1.07 Gpixels/sec |
| 0.81 Gpixels/sec | Feature Matching | 0.5 Gpixels/sec |
| 270.9 Gpixels/sec | Stereo Matching | 163 Gpixels/sec |
| 9339.7 FPS | Particle Physics | 5820.4 FPS |
| OpenCL | API | OpenCL |
| 12503 | G3D Mark Score | 10431 |
| 918 | G2D Mark | 1094 |
| 90 FPS | DirectX 11 | 79 FPS |
| 59 FPS | DirectX 12 | 46 FPS |
| 6438 Ops/s | GPU Compute | 5066 Ops/s |
| 11848 | GB6 ML Single Precision | — |
| 21368 | GB6 ML Half Precision | — |
| 7905 | GB6 ML Quantized | — |
| 4958 | Image Classification (SP) | — |
| 12747 | Image Segmentation (HP) | — |
| 9816 | Image Super Resolution (Q) | — |
| 22467 | Face Detection (HP) | — |
| 41362 | Pose Estimation (Q) | — |
| 2563 | Text Classification (SP) | — |
| 3721 | Machine Translation (HP) | — |
| 5929 | Object Detection (SP) | — |
| 18361 | Depth Estimation (Q) | — |
| 84665 | Style Transfer (SP) | — |
| ONNX | Framework | — |
| DirectML | Backend | — |
| 57 GPixel/s | Pixel Fill Rate | 90 GPixel/s |
| 142 GTexel/s | Texture Fill Rate | 179 GTexel/s |
| 9.1 TFLOPS | FLOPS (FP32) | 5.7 TFLOPS |
| GDDR6 | Memory Type | System Shared |
| 8 GB | Memory Size | — |
| 1750 MHz | Memory Clock | — |
| 14000 Mbps | Effective Memory Speed | — |
| 128-bit | Bus | — |
| No | ECC | — |
| 224 GB/s | Memory Bandwidth | — |
| PCIe 4.0 x8 | Interface | PCIe 5.0 x16 |
| 130 W | TGP | 45-120 W (configurable) |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 4 nm |
| 276 mm² | Die Size | 308 mm² |
| 12 billion | Transistor Count | — |
| 43.48 MTr/mm² | Transistor Density | — |
| 12 | DirectX | 12.2 |
| 1.3 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.1 |
| 8.6 | CUDA | No |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | No |
| 1.4a | DisplayPort | 2.1a |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| January 27, 2022 | Released | January 7, 2025 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Generic |
| Entry-level | Segment | Mid-range |
| Ampere | Architecture | RDNA 3.5 |
| GA106 | GPU Codename | Strix Halo |
| -Intel Core i5 12400or above | Recommended CPU | -AMD Ryzen AI Max Pro 380or above |
| 6352 | Steel Nomad Lite Score | — |
| 6235 | Time Spy | — |
| 30139 | Solar Bay | — |
| 3545 | Port Royal | — |
| 15968 | Fire Strike | — |
| 12803 | Wild Life Extreme | — |
| 74799 | Night Raid | — |
| 1552 MHz | Base Clock | 1295 MHz |
| 1777 MHz | Boost Clock | 2800 MHz |
| 2560 | Shading Units | 1024 |
| 80 | Texture Mapping Units (TMUs) | 64 |
| 32 | Render Output Units (ROPs) | 32 |
| 20 | Compute Units (Pipelines) | 16 |
| 80 | Tensor Cores | No |
| 20 | Ray-tracing Cores | 16 |
| 128KB per cluster | L1 Cache | 512KB per cluster |
| 2MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |