From what we know so far, Nvidia awaits CES 2025, which will take place in the first days of January to officially launch the long-awaited new generation of graphics cards, the RTX50. But in the meantime, and as is normal at this stage, leaks and rumors follow one another, and on this occasion new data has appeared on the next NVIDIA RTX 5080the second most powerful in the family, but everything still indicates that it would be a real beast… and not just for games.
The NVIDIA GeForce RTX 5090 and RTX 5080 GPUs will be the high-end graphics cards of the new Blackwell generation, and if it happens like in previous generati ons, they will be the first to see the light of day. We already “know” a lot about them through leaks and rumors, but new information ensures that the RTX 5080 will have a faster VRAM solution… in fact, the fastest on the market today.
More memory and faster
Apparently, the GeForce RTX 5080 which will use the GB203 GPU will be equipped with 16 GB GDDR7 memory at an effective speed of 32 Gbps (i.e. 4 Gbps more than the 28 Gbps that the RTX 5090 will theoretically have), under a 256-bit bus and which, in total, would offer up to 1 TB/s of memory bandwidth.
If we compare it to the current RTX 4080, it has a bandwidth of 736 GB/s since it has GDDR6X VRAM at 23 Gbps. This memory is already crazy, but GDDR7 seems to want to change the rules of the game again with a bandwidth that is hard to believe for a 256-bit bus.
It is necessary to take into account, and it is curious, that apparently only the RTX 5080 will have this type of memory, at least at 32 Gbps; Other models in the RTX 50 family will also use GDDR7, but as far as we know, none at this speed.
Everything we know about the RTX 5080
According to all the leaks and rumors we have had so far, the NVIDIA GeForce RTX 5080 will be based on the PG144/147-SKU45 PCB and will feature the NVIDIA Blackwell GB203-400-A1 chip. This graphics card will use everything the chip provides, i.e. it will not be a “capped” model, meaning it would have 84 SMs and a total of 10,752 cores, or 51%. less than the RTX 5090.
We also know that this graphics card will have a TBP (Total Board Power, i.e. general consumption of the entire device, not just the GPU) of 400 watts, which represents an increase of 25 % of the power wall, although it must be kept in mind that between the figures given by the manufacturer and those that we will obtain later in the real world we can find a significant gap.
That said, NVIDIA is expected to offer 16GB and 24GB models of this graphics card. This would be a really nice improvement, especially for gamers and professionals who want to use that extra memory for content creation, AI-intensive tasks, or just to ensure high-resolution games have enough VRAM to load games. textures and maps.
