Specifications and PCB:
The technical specifications:
In terms of frequency, the base frequency is announced at 2205 MHz while the Boost is at 2565 MHz. The 16 GB of G-DDR6X memory run at 1400 MHz (716.8 GB/s) on a 256 bit bus. Our KFA2 RTX 4080 SG benefits from a slight factory overclocking, since the reference card, the RTX 4080 Founders Edition, has a Boost frequency of 2505 MHz. Via the KFA2 utility and the 1-click-OC function, you can raise it to 2580 MHz.
A small passage through GPU-Z to check that the information read is correct. The GPU frequency is 2205 MHz, and the Boost frequency is 2565 MHz. Don’t forget that the latter will be higher during benchmarks depending on the quality of your chip and determined by GPU Boost 4.0. The memory has a frequency of 1400 MHz. We can also notice that the power limit can be increased by 31% to reach 420 watts. I’m looking forward to testing the overclocking on this model.
Let’s unpack the PCB:
For obvious reasons of timing with our three copies of RTX 4080 to test, we did not undertake the disassembly of our cards at first. This will be done in the coming days in order to update this article. We will come back to the details of the different PCBs in a dedicated article.
However, we know that it consists of 16 + 3 phases and 8 GDDR6X memory chips of 2 GB. The RTX 4080 uses a PCIe 4.0 x16 interface but its power architecture is compliant with PCIe Gen 5 specifications.