Quick/Comparisons
25 | Workstation | 100 |
18 | AI/ML | 93 |
59 | Energy Efficiency |
Compare with something else?
Compare GeForce RTX 3050 with another →49 |
27 | Quick Comparison Final Score | 98 |
18 | Gaming | 99 |
| GA107 | Graphics Processor | GB202-300-A1 |
| 2048 | Cores | 24064 |
| 64 / 40 | TMUs / ROPs | 752 / 190 |
| 1162.84 | Blender GPU | 16644.8 |
| 44 | Forza Horizon 5 | 230 |
| 55 | The Witcher 3 | 304 |
| 80 | Counter-Strike 2 | 259 |
| 53 | Far Cry 6 | 198 |
| 27 | Hogwarts Legacy | 192 |
| 39 | Call of Duty | 301 |
| 24 | Ghost of Tsushima | 172 |
| 34 | Cyberpunk 2077 | 221 |
| 59 | Tomb Raider | 303 |
| 46 | Average FPS | 242 |
| 60 | 1080p High | 282 |
| 46 | 1080p Ultra | 242 |
| 32 | 1440p Ultra | 197 |
| 17 | 4K Ultra | 118 |
| Low | Margin of Error | High |
| 58733 | GB6 Compute Score | 419470 |
| 88.6 img/sec | Background Blur | 366.1 img/sec |
| 57.3 img/sec | Face Detection | 248 img/sec |
| 2.53 Gpixels/sec | Horizon Detection | 23.3 Gpixels/sec |
| 3.33 Gpixels/sec | Edge Detection | 35.2 Gpixels/sec |
| 2.55 Gpixels/sec | Gaussian Blur | 45 Gpixels/sec |
| 0.76 Gpixels/sec | Feature Matching | 2.47 Gpixels/sec |
| 256.5 Gpixels/sec | Stereo Matching | 3040 Gpixels/sec |
| 7465.5 FPS | Particle Physics | 42574.6 FPS |
| OpenCL | API | OpenCL |
| 9493 | G3D Mark Score | 37305 |
| 490 | G2D Mark | 1375 |
| 71 FPS | DirectX 11 | 338 FPS |
| 46 FPS | DirectX 12 | 153 FPS |
| 3860 Ops/s | GPU Compute | 26895 Ops/s |
| 10038 | GB6 ML Single Precision | 50053 |
| 19152 | GB6 ML Half Precision | 74036 |
| 6984 | GB6 ML Quantized | 37636 |
| 4349 | Image Classification (SP) | 16903 |
| 11416 | Image Segmentation (HP) | 48518 |
| 8973 | Image Super Resolution (Q) | 54618 |
| 18927 | Face Detection (HP) | 103224 |
| 34631 | Pose Estimation (Q) | 338587 |
| 2269 | Text Classification (SP) | 3894 |
| 3539 | Machine Translation (HP) | 7291 |
| 5046 | Object Detection (SP) | 26498 |
| 15772 | Depth Estimation (Q) | 90853 |
| 75260 | Style Transfer (SP) | 635289 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 42-70 GPixel/s | Pixel Fill Rate | 497 GPixel/s |
| 68-111 GTexel/s | Texture Fill Rate | 1968 GTexel/s |
| 4.3-7.1 TFLOPS | FLOPS (FP32) | 126 TFLOPS |
| GDDR6 | Memory Type | GDDR7 |
| 4 GB | Memory Size | 96 GB |
| 1500 MHz | Memory Clock | 1750 MHz |
| 12000 Mbps | Effective Memory Speed | 28000 Mbps |
| 128-bit | Bus | 512-bit |
| No | ECC | Yes |
| 192 GB/s | Memory Bandwidth | 1792 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 5.0 x16 |
| 35-95 W (configurable) | TGP | 600 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 5 nm |
| 200 mm² | Die Size | 750 mm² |
| 8.7 billion | Transistor Count | 92.2 billion |
| 43.5 MTr/mm² | Transistor Density | 122.93 MTr/mm² |
| 12 | DirectX | 12.2 |
| 1.2 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.6 | CUDA | 12 |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | DLSS 4 |
| 1.4a | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 1, 2021 | Released | March 18, 2026 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Professional |
| Mid-range | Segment | High-end |
| Ampere | Architecture | Blackwell 2.0 |
| GA107 | GPU Codename | GB202-300-A1 |
| — | Recommended CPU | -AMD Ryzen 9 9955HX3Dor above |
| 4914 | Steel Nomad Lite Score | 50516 |
| 4884 | Time Spy | 42437 |
| 21603 | Solar Bay | 258808 |
| 552 | Port Royal | 39952 |
| 12561 | Fire Strike | 72183 |
| 9421 | Wild Life Extreme | 110070 |
| 53654 | Night Raid | 216213 |
| 712-1530 MHz (configurable) | Base Clock | 1590 MHz |
| 1057-1740 MHz (configurable) | Boost Clock | 2617 MHz |
| 2048 | Shading Units | 24064 |
| 64 | Texture Mapping Units (TMUs) | 752 |
| 40 | Render Output Units (ROPs) | 190 |
| 16 | Compute Units (Pipelines) | 188 |
| 64 | Tensor Cores | 752 |
| 16 | Ray-tracing Cores | 188 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 2MB shared | L2 Cache | 128MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |