AMD Radeon RX 9070 vs NVIDIA GeForce RTX 3080
In the PassMark G3D benchmark the AMD Radeon RX 9070 scores 25,382 against 24,996 for the NVIDIA GeForce RTX 3080, making it about 2 percent faster than the NVIDIA GeForce RTX 3080.
The AMD Radeon RX 9070 carries more video memory (16 GB against 10 GB), which matters at higher resolutions and for larger workloads.
The AMD Radeon RX 9070 draws less board power (220 W against 320 W).
Measured as benchmark score per watt, the AMD Radeon RX 9070 is the more efficient of the two (115.4 against 78.1 points per watt).
Comparing 15 specifications that differ between these two cards. Coverage: 10/10 recorded for the AMD Radeon RX 9070, 10/10 for the NVIDIA GeForce RTX 3080. Fields neither card records are omitted; fields only one records are shown as "Not recorded".
Specifications compared
| AMD Radeon RX 9070 | NVIDIA GeForce RTX 3080 | |
|---|---|---|
| Shading units | 3,584 | 8,704 |
| Compute units | 56 | Not recorded |
| Ray tracing cores | 56 | 68 |
| Tensor cores | 112 | 272 |
| Base clock | 2.07 GHz | 1.44 GHz |
| Boost clock | 2.52 GHz | 1.71 GHz |
| Memory size | 16 GB | 10 GB |
| Memory type | GDDR6 | GDDR6X |
| Memory bus width | 256-bit | 320-bit |
| Memory bandwidth | 640.0 GB/s | 760.3 GB/s |
| Board power | 220 W | 320 W |
| Process node | Not recorded | 8 nm |
| Die size | 357 mm² | 628 mm² |
| Transistors | 53,900 M | 28,300 M |
| Architecture | RDNA 4 | Ampere |
| Launch date | 2025-03-06 | 2020-09-17 |
| PassMark G3D | 25,382 | 24,996 |