NVIDIA GeForce RTX 3090 Ti vs NVIDIA GeForce RTX 5070
In the PassMark G3D benchmark the NVIDIA GeForce RTX 3090 Ti scores 29,262 against 28,677 for the NVIDIA GeForce RTX 5070, making it about 2 percent faster than the NVIDIA GeForce RTX 5070.
The NVIDIA GeForce RTX 3090 Ti carries more video memory (24 GB against 12 GB), which matters at higher resolutions and for larger workloads.
The NVIDIA GeForce RTX 5070 draws less board power (250 W against 450 W).
Measured as benchmark score per watt, the NVIDIA GeForce RTX 5070 is the more efficient of the two (114.7 against 65.0 points per watt).
Comparing 16 specifications that differ between these two cards. Coverage: 10/10 recorded for the NVIDIA GeForce RTX 3090 Ti, 10/10 for the NVIDIA GeForce RTX 5070. Fields neither card records are omitted; fields only one records are shown as "Not recorded".
Specifications compared
| NVIDIA GeForce RTX 3090 Ti | NVIDIA GeForce RTX 5070 | |
|---|---|---|
| Shading units | 10,752 | 6,144 |
| Ray tracing cores | 84 | 48 |
| Tensor cores | 336 | 192 |
| Base clock | 1.56 GHz | 2.33 GHz |
| Boost clock | 1.86 GHz | 2.51 GHz |
| Memory size | 24 GB | 12 GB |
| Memory type | GDDR6X | GDDR7 |
| Memory bus width | 384-bit | 192-bit |
| Memory bandwidth | 1,008.0 GB/s | 672.0 GB/s |
| Board power | 450 W | 250 W |
| Process node | 8 nm | 4 nm |
| Die size | 628 mm² | 263 mm² |
| Transistors | 28,300 M | 31,100 M |
| Architecture | Ampere | Blackwell |
| Launch date | 2022-03-29 | 2025-03-04 |
| PassMark G3D | 29,262 | 28,677 |