RTX 3090 vs RTX 4070: Specs
Architecture, compute capability and supported precisions for the RTX 3090 and the RTX 4070, 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 3090 | RTX 4070 |
|---|---|---|
| VRAM | 24GB GDDR6X | 12GB GDDR6X |
| Memory bandwidth | 936 GB/s | 504 GB/s |
| Architecture | Ampere | Ada Lovelace |
| Compute capability | 8.6 | 8.9 |
| Precisions in hardware | FP32, FP16, BF16, INT4 | FP32, FP16, BF16, FP8, INT4 |
| Peak FP16/BF16 tensor TFLOPS | 142 TFLOPS | 116.6 TFLOPS |
| Peak FP8 tensor TFLOPS | – | 233.2 TFLOPS |
| NVLink / multi-GPU interconnect | NVLink, 2-way | – |
| Max board power (TDP) | 350W | 200W |
