Quick/Comparisons
A entry-level Nvidia GeForce RTX 3060 Ti graphics card with modest workstation performance (42/100), higher power consumption. Suited for casual gaming and basic graphics tasks.
| Gaming | 38 /100 |
| Workstation | 42 /100 |
| AI/ML | 31 /100 |
| Energy Efficiency | 35 |
Looking for more comparisons?
Compare GeForce RTX →| Quick Comparison Final Score | 38 /100 |
| Graphics Processor | GA104 |
| Cores | 4864 |
| TMUs / ROPs | 152 / 80 |
| Blender GPU | 2992.04 |
| Forza Horizon 5 | 87 |
| The Witcher 3 | 124 |
| Counter-Strike 2 | 167 |
| Far Cry 6 | 106 |
| Hogwarts Legacy | 71 |
| Call of Duty | 100 |
| Ghost of Tsushima | 68 |
| Cyberpunk 2077 | 82 |
| Tomb Raider | 128 |
| Average FPS | 104 |
| 1080p High | 127 |
| 1080p Ultra | 104 |
| 1440p Ultra | 77 |
| 4K Ultra | 43 |
| Margin of Error | Low |
| GB6 Compute Score | 115518 |
| Background Blur | 185.1 img/sec |
| Face Detection | 108.4 img/sec |
| Horizon Detection | 5.35 Gpixels/sec |
| Edge Detection | 7.17 Gpixels/sec |
| Gaussian Blur | 5.54 Gpixels/sec |
| Feature Matching | 1.15 Gpixels/sec |
| Stereo Matching | 478 Gpixels/sec |
| Particle Physics | 15183 FPS |
| API | OpenCL |
| G3D Mark Score | 20272 |
| G2D Mark | 990 |
| DirectX 11 | 164 FPS |
| DirectX 12 | 78 FPS |
| GPU Compute | 9905 Ops/s |
| GB6 ML Single Precision | 17811 |
| GB6 ML Half Precision | 29969 |
| GB6 ML Quantized | 11367 |
| Image Classification (SP) | 7384 |
| Image Segmentation (HP) | 19320 |
| Image Super Resolution (Q) | 16108 |
| Face Detection (HP) | 34615 |
| Pose Estimation (Q) | 74811 |
| Text Classification (SP) | 2638 |
| Machine Translation (HP) | 4136 |
| Object Detection (SP) | 8718 |
| Depth Estimation (Q) | 25946 |
| Style Transfer (SP) | 153275 |
| Framework | ONNX |
| Backend | DirectML |
| Pixel Fill Rate | 133 GPixel/s |
| Texture Fill Rate | 253 GTexel/s |
| FLOPS (FP32) | 16.2 TFLOPS |
| Memory Type | GDDR6 |
| Memory Size | 8 GB |
| Memory Clock | 1750 MHz |
| Effective Memory Speed | 14000 Mbps |
| Bus | 256-bit |
| ECC | No |
| Memory Bandwidth | 448 GB/s |
| Interface | PCIe 4.0 x16 |
| TGP | 200 W |
| Manufacturing | Samsung |
| Fabrication Process | 8 nm |
| Die Size | 392 mm² |
| Transistor Count | 17 billion |
| Transistor Density | 43.37 MTr/mm² |
| DirectX | 12 |
| Vulkan | 1.3 |
| OpenGL | 4.6 |
| OpenCL | 3 |
| CUDA | 8.6 |
| Ray Tracing | Yes |
| DLSS | DLSS 2 |
| DisplayPort | 1.4a |
| Vendor | Nvidia |
| Build | Discrete |
| Released | December 2, 2020 |
| Case | Desktop |
| Purpose | Gaming |
| Segment | Mid-range |
| Architecture | Ampere |
| GPU Codename | GA104 |
| Recommended CPU | -Intel Core i5 12600Kor above |
| Steel Nomad Lite Score | 11978 |
| Time Spy | 11707 |
| Solar Bay | 54374 |
| Port Royal | 6971 |
| Fire Strike | 29568 |
| Wild Life Extreme | 24415 |
| Night Raid | 109854 |
| Instructions Per Cycle | 2 IPC |
| Base Clock | 1410 MHz |
| Boost Clock | 1665 MHz |
| Shading Units | 4864 |
| Texture Mapping Units (TMUs) | 152 |
| Render Output Units (ROPs) | 80 |
| Compute Units (Pipelines) | 38 |
| Tensor Cores | 152 |
| Ray-tracing Cores | 38 |
| L1 Cache | 128KB per cluster |
| L2 Cache | 4MB shared |
84/100