NVIDIA GeForce RTX 3060
NVIDIA launched the GeForce RTX 3060 in early 2021 as an upper mainstream graphics card for flawless 1080p gaming. Built using the efficient 8nm process, it packs 12GB of GDDR6 memory and taps into their Ampere architecture for serious performance.
Key specs include 12 billion transistors on the GA106 GPU, 6GB of VRAM, and support for advanced graphics features like real-time ray tracing. By delivering faster speeds than previous 60-class cards, plus modern connectivity, the RTX 3060 brings cutting-edge visuals to popular online titles, competitive esports, and AAA blockbuster games.
Specs And Benchmark
Board Design
| Available | Jan 2021 |
| Foundry | Samsung |
| Type | Desktop |
| Interface | PCIe 4.0 x16 |
| Generation | GeForce 30 |
| Outputs | 1x HDMI, 2.1 3x DisplayPort 1.4a |
| Power Connectors | 1x 12-pin |
| TDP | 170W |
| Suggested PSU | 450W |
GPU Features
| DirectX | 12 Ultimate (12_2) |
| OpenGL | 4.6 |
| OpenCL version | 3.0 |
| Vulkan version | 1.3 |
| Shader Model | 6.6 |
| CUDA | 8.6 |
Graphics Processor
| Die Size | 276mm² |
| GPU Variant | GA106-300-A1 |
| GPU name | GA106 |
| Transistor count | 12,000 million |
| Architecture | Ampere |
| Process Node | 8 nm |
Clock Speeds
| Boost Clock | 1777MHz |
| Base Clock | 1320MHz |
| Memory Clock | 1875MHz |
Memory Specs
| Memory Types | GDDR6 |
| Max Memory Size | 12GB |
| Max Memory Bandwidth | 360.0 GB/s |
| Memory Bus | 192bit |
Render Config
| Shading units | 3584 |
| L1 cache | 128 KB (per SM) |
| L2 cache | 3MB |
| TMUs | 112 |
| ROPs | 48 |
| GPU Major Cores | 28 |
Theoretical Performance
| FP16 (half) | 12.74 TFLOPS |
| FP32 (float) | 12.74 TFLOPS |
| FP64 (double) | 199.0 GFLOPS |
| Texture Rate | 199.0 GTexel/s |
| Pixel Rate | 85.30 GPixel/s |
