For a few months we have known that the new NVIDIA graphics cards will arrive in a few months, since they will be presented during CES while they would have a launch during the first months of the year, this being the reason why we know more details about them. In this case, we now know that the company that created the RTX has once again resorted to Samsung for the memory that will incorporate the series 50leaving aside those from Micron that we have seen during the last two generations to once again resort to those offered by the South Korean company.
There are three key companies that currently develop video memories, as we well know, they are SK Hynix, Samsung and Micron, which offer solutions of all kinds, making it difficult for certain brands to choose between one and the other since each one has its strengths. After having used Micron memories for two entire generations, NVIDIA wants to hit again Samsung a great role, since the desktop computer versions of its new graphics cards will have the memory GDDR7 from this company, while in the laptop companies they will use all three, but they will also give them priority over the other two companies.
One of the biggest victories of this year Samsung, getting NVIDIA to use its memories
As we well know, Samsung has not been going through its best moment, the semiconductor manufacturer has quite a few problems in offering advances in the race for nodes less than 3 nm, while in other aspects such as AI, they are not managing to stand out either. too much. That is why the fact that NVIDIA has chosen to use the video memories they have developed is quite a victory, and even more so considering that they had not collaborated with them in this aspect for quite some time because there was another company that had much more. priority.
As indicated by the Korean media Greened.kr, NVIDIA has chosen to use Samsung’s GDDR7 memories due to 28 Gbps and 32 Gbps in its next generation, offering a fairly large improvement compared to previous series. One of the most important data that we must know about how the RTX graphics will incorporate this VRAM memory is in the fact that the RTX 5080 will be the one that incorporates the 32 Gbps ones, while the rest will use the 28 Gbps one, something that in A beginning may seem strange, but it has certain reasons.
In this case, NVIDIA has chosen to use 28 Gbps memory in the RTX 5090 because the interface it uses is the widest 512 bits, something that, by using many more memory chips, could directly affect the energy consumption of the entire board. Even so, the increase in bandwidth that this GPU will have is quite large, and we are talking about it being able to reach up to 1792 GB/s, 78% more compared to the 1008 GB/s that it is capable of. reach the RTX 4090, so the fact that it incorporates “inferior” memory does not mean that it will have worse performance.