Head-to-head
GeForce RTX 4080 SUPER vs GeForce RTX 5080
Key differences
- RTX 5080 has 30% more memory bandwidth (960 GB/s vs 736 GB/s).
- RTX 5080 is rated for more power: 360 W against 320 W.
Specifications
| GeForce RTX 4080 SUPER | GeForce RTX 5080 | |
|---|---|---|
| Architecture | Ada Lovelace | Blackwell |
| Launch | 31 Jan 2024 | 30 Jan 2025 |
| US launch price | $999 | $999 |
| GPU / chip | AD103 | GB203 |
| Process | TSMC 4N | TSMC 4N |
| Transistors | 45.9 billion | 45.6 billion |
| Die size | 379 mm² | 378 mm² |
| Streaming multiprocessors | 80 | 84 |
| CUDA cores | 10,240 | 10,752 |
| Tensor Cores | 320 | 336 |
| RT cores | 80 | 84 |
| ROPs | 112 | 112 |
| Base clock | 2,295 MHz | 2,295 MHz |
| Boost clock | 2,550 MHz | 2,617 MHz |
| L2 / last-level cache | 64 MB | 64 MB |
| Capacity | 16 GB | 16 GB |
| Type | GDDR6X | GDDR7 |
| Bus width | 256-bit | 256-bit |
| Data rate | 23 Gbps | 30 Gbps |
| Bandwidth | 736 GB/s | 960 GB/s |
| FP32 (shader) | 52.2 TFLOPS | 56.3 TFLOPS |
| AI TOPS (vendor figure) | 836 | 1,801 |
| Power | 320 W | 360 W |
| Power connector | 16-pin 12VHPWR | 16-pin 12V-2×6 |
| Host interface | PCIe 4.0 ×16 | PCIe 5.0 ×16 |
| Display outputs | 3× DisplayPort 1.4a, 1× HDMI 2.1 | 3× DisplayPort 2.1b, 1× HDMI 2.1b |
| NVENC | 2× 8th gen | 2× 9th gen |
Values in bold differ between the two. A dash means the spec does not apply to that brand.
Launch price by country
| RTX 4080 SUPER | RTX 5080 | |
|---|---|---|
| United States | $999 | $999 |
| India | — | ₹1,07,000 |
| United Kingdom | — | £979 |
| Eurozone (Germany) | — | €1,169 |
| Japan | — | ¥198,800 |
| Australia | — | A$2,019 |
Independent reviews
Not sure which to pick? Try the GPU finder. Full spec sheets: GeForce RTX 4080 SUPER · GeForce RTX 5080.
More comparisons: RTX 5080 vs RTX 5090 · RTX 5070 Ti vs RTX 5080