RTX 2080 Ti vs RTX 4070 Ti: Specs
Architecture, compute capability and supported precisions for the RTX 2080 Ti and the RTX 4070 Ti, from vendor datasheets.
No live price to compare
No provider on Aquanode is listing at least one of these two cards right now, so no hourly rate is shown. This page shows live prices as soon as both are listed.
Specs side by side
| Spec | RTX 2080 Ti | RTX 4070 Ti |
|---|---|---|
| VRAM | 11GB GDDR6 | 12GB GDDR6X |
| Memory bandwidth | 616 GB/s | 504 GB/s |
| Architecture | Turing | Ada Lovelace |
| Compute capability | 7.5 | 8.9 |
| Precisions in hardware | FP32, FP16, INT4 | FP32, FP16, BF16, FP8, INT4 |
| Peak FP16/BF16 tensor TFLOPS | 107.6 TFLOPS | 160.4 TFLOPS |
| Peak FP8 tensor TFLOPS | – | 320.7 TFLOPS |
| NVLink / multi-GPU interconnect | NVLink, 2-way, 100 GB/s bidirectional | – |
| Max board power (TDP) | 250W (260W Founders Edition) | 285W |
