AMD Radeon AI PRO R9700 vs NVIDIA GeForce RTX 4070
In the PassMark G3D benchmark the AMD Radeon AI PRO R9700 scores 26,987 against 26,875 for the NVIDIA GeForce RTX 4070, making it effectively tied with the NVIDIA GeForce RTX 4070.
The AMD Radeon AI PRO R9700 carries more video memory (32 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 300 W).
Measured as benchmark score per watt, the NVIDIA GeForce RTX 4070 is the more efficient of the two (134.4 against 90.0 points per watt).
Comparing 15 specifications that differ between these two cards. Coverage: 10/10 recorded for the AMD Radeon AI PRO R9700, 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
| AMD Radeon AI PRO R9700 | NVIDIA GeForce RTX 4070 | |
|---|---|---|
| Shading units | 4,096 | 5,888 |
| Compute units | 64 | Not recorded |
| Ray tracing cores | 64 | 46 |
| Tensor cores | 128 | 184 |
| Base clock | 1.66 GHz | 1.92 GHz |
| Boost clock | 2.92 GHz | 2.48 GHz |
| Memory size | 32 GB | 12 GB |
| Memory type | GDDR6 | GDDR6X |
| Memory bus width | 256-bit | 192-bit |
| Memory bandwidth | 640.0 GB/s | 504.0 GB/s |
| Board power | 300 W | 200 W |
| Process node | Not recorded | 5 nm |
| Die size | 357 mm² | 294 mm² |
| Transistors | 53,900 M | 35,800 M |
| Architecture | RDNA 4 | Ada Lovelace |
| Launch date | 2025-07-23 | 2023-04-13 |
| PassMark G3D | 26,987 | 26,875 |