NVIDIA GeForce RTX 3060 vs NVIDIA GeForce RTX 5050
In the PassMark G3D benchmark the NVIDIA GeForce RTX 5050 scores 16,917 against 16,887 for the NVIDIA GeForce RTX 3060, making it effectively tied with the NVIDIA GeForce RTX 3060.
The NVIDIA GeForce RTX 3060 carries more video memory (12 GB against 8 GB), which matters at higher resolutions and for larger workloads.
The NVIDIA GeForce RTX 5050 draws less board power (130 W against 170 W).
Measured as benchmark score per watt, the NVIDIA GeForce RTX 5050 is the more efficient of the two (130.1 against 99.3 points per watt).
Comparing 15 specifications that differ between these two cards. Coverage: 10/10 recorded for the NVIDIA GeForce RTX 3060, 10/10 for the NVIDIA GeForce RTX 5050. Fields neither card records are omitted; fields only one records are shown as "Not recorded".
Specifications compared
| NVIDIA GeForce RTX 3060 | NVIDIA GeForce RTX 5050 | |
|---|---|---|
| Shading units | 3,584 | 2,560 |
| Compute units | 28 | Not recorded |
| Ray tracing cores | 28 | 20 |
| Tensor cores | 112 | 80 |
| Base clock | 1.32 GHz | 2.32 GHz |
| Boost clock | 1.78 GHz | 2.57 GHz |
| Memory size | 12 GB | 8 GB |
| Memory bus width | 192-bit | 128-bit |
| Memory bandwidth | 360.0 GB/s | 320.0 GB/s |
| Board power | 170 W | 130 W |
| Process node | 8 nm | 5 nm |
| Die size | 276 mm² | 149 mm² |
| Transistors | 12,000 M | 16,900 M |
| Architecture | Ampere | Blackwell |
| Launch date | 2021-02-25 | 2025-07-01 |
| PassMark G3D | 16,887 | 16,917 |