NVIDIA GeForce RTX 3090 vs NVIDIA GeForce RTX 4070
In the PassMark G3D benchmark the NVIDIA GeForce RTX 4070 scores 26,875 against 26,512 for the NVIDIA GeForce RTX 3090, making it about 1 percent faster than the NVIDIA GeForce RTX 3090.
The NVIDIA GeForce RTX 3090 carries more video memory (24 GB against 12 GB), which matters at higher resolutions and for larger workloads.
The NVIDIA GeForce RTX 4070 draws less board power (200 W against 350 W).
Measured as benchmark score per watt, the NVIDIA GeForce RTX 4070 is the more efficient of the two (134.4 against 75.7 points per watt).
Comparing 15 specifications that differ between these two cards. Coverage: 10/10 recorded for the NVIDIA GeForce RTX 3090, 10/10 for the NVIDIA GeForce RTX 4070. Fields neither card records are omitted; fields only one records are shown as "Not recorded".
Specifications compared
| NVIDIA GeForce RTX 3090 | NVIDIA GeForce RTX 4070 | |
|---|---|---|
| Shading units | 10,496 | 5,888 |
| Ray tracing cores | 82 | 46 |
| Tensor cores | 328 | 184 |
| Base clock | 1.40 GHz | 1.92 GHz |
| Boost clock | 1.70 GHz | 2.48 GHz |
| Memory size | 24 GB | 12 GB |
| Memory bus width | 384-bit | 192-bit |
| Memory bandwidth | 936.2 GB/s | 504.0 GB/s |
| Board power | 350 W | 200 W |
| Process node | 8 nm | 5 nm |
| Die size | 628 mm² | 294 mm² |
| Transistors | 28,300 M | 35,800 M |
| Architecture | Ampere | Ada Lovelace |
| Launch date | 2020-09-24 | 2023-04-13 |
| PassMark G3D | 26,512 | 26,875 |