GeForce RTX 4080 Super vs GeForce RTX 4070
Dashed outline = score at launch
Why GeForce RTX 4080 Super is better
- VRAM: 16 GB GDDR6X vs 12 GB GDDR6X(33% more)
- Memory Bus: 256-bit vs 192-bit(33% more)
- Boost Clock: 2550 MHz vs 2475 MHz(higher)
Why GeForce RTX 4070 is better
- TDP: 200 W vs 320 W(1.6× less)
Verdict
GeForce RTX 4080 Super leads outright in 4 of 6 dimensions today.
Spec by spec
| Spec | GeForce RTX 4080 Super | GeForce RTX 4070 |
|---|---|---|
| Performance | ||
| Compute Units | 10240 CUDA cores | — |
| Boost Clock | 2550 MHz● | 2475 MHz |
| Process Node | 4 nm | — |
| Memory | ||
| VRAM | 16 GB GDDR6X● | 12 GB GDDR6X |
| Memory Bus | 256-bit● | 192-bit |
| Memory Bandwidth | 736 GB/s | — |
| Bandwidth | — | 504 GB/s |
| Power | ||
| TDP | 320 W | 200 W● |
| Recommended PSU | 750 W | — |
| Core | ||
| CUDA Cores | — | 5888 |
| Boost Clock | 2550 MHz● | 2475 MHz |
| Architecture | — | Ada Lovelace |
| Power & Output | ||
| TDP | 320 W | 200 W● |
| Outputs | — | 3x DP, 1x HDMI |