Nvidia has released the hardware specifications for their upcoming GTX 1070 that is set to release alongside the GTX 1080 as the next generation graphics cards.
Nvidia GTX 1070 is the cheaper sibling of GTX 1080 and from the detailed specifications, it appear to be a little behind GTX 1080, although with a much more attractive price. You can check out the full system specifications below and see how they compare against GTX 1080.
| Architecture | Pascal 16nm FinFET | Pascal 16nm FinFET |
|---|---|---|
| GPU | GP104-400 | GP104-200 |
| Streaming Multiprocessors | 20 | 15 |
| CUDA Cores | 2560 | 1920 |
| TMUs | 160 | 120 |
| ROPs | 64 | 64 (TBC) |
| FP32 Computing Power (Base Clock) | 8.2 TFLOPs | 5.8 TFLOPs |
| FP32 Computing Power (Boost Clock) | 8.9 TFLOPs | 6.5 TFLOPs |
| Memory Type | 8GB GDDR5X | 8GB GDDR5 |
| Base Clock | 1607 MHz | 1506 MHz |
| Boost Clock | 1733 MHz | 1683 MHz |
| Memory Clock | 1250 MHz | 2000 MHz |
| Effective Memory Clock | 10000 MHz | 8000 MHz |
| Memory Bus | 256-bit | 256-bit |
| Memory Bandwidth | 320 GB/s | 256 GB/s |
| TDP | 180W | 150W |
| Power Connectors | 1x 8pin | 1x 8pin |
| MSRP | $599 Base Price $699 FE |
$379 Base Price $449 FE |
While GTX 1070 won’t be out until June 10th, we should be getting benchmarks for it as the release date draws near. It should be interesting to compare the performance between both of these graphics card considering the price difference.
Let us know what you think about these specifications in the comments below.
