Both GPUs will get 16GB of video memory running on GDDR7 but with different data transfer rates.
RTX 5080 will be built on the GB203-400-A1 core and equipped with 10,752 CUDA cores. The video card uses a 256-bit memory bus and GDDR7 modules with a bandwidth of up to 1024 GB/s.
The power consumption of the card is 400 W, which will be 25% more than previous models, but it also offers record memory speeds.
The RTX 5070 Ti will get a GB203-300-A1 core with 8960 CUDA cores and the same 256-bit memory bus. However, the speed of GDDR7 memory will be lower, up to 896 GB/s. The power consumption of the graphics card is expected to be in the range of 300-350 W.
Both graphics cards will be part of the next generation NVIDIA Blackwell, which will be introduced in January 2025.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
