GDDR6X memory played a very important role in the current generation of NVIDIA graphics cards, the GeForce RTX 30. As some of our readers may remember said memory was jointly developed by NVIDIA and Micronwhich explains why the green giant was the only company that had access to it, giving it a huge advantage over AMD, which could only use GDDR6 memories.

For comparison, it is enough to recall that the Radeon RX 6000 only used GDDR6 memory at a maximum of 16 GHz when it debuted, while NVIDIA was able to fit 19.5 GHz GDDR6X memory into the GeForce RTX 3090. This memory peaked with the GeForce RTX 3090 Ti, which installs chips at a frequency of 21 GHz, the fact is that Micron continued to improve this graphics memory standard, and according to new information, the production of graphics memory chips has already begun. Memory 2GB (16Gb) GDDR6X at 24GHz.

It is not yet clear which graphics cards within the GeForce RTX 40 series will use these new chips, but I believe that most likely 24 GHz chips are limited to GeForce RTX 4090and that 21 GHz chips are used in the GeForce RTX 4080 and GeForce RTX 4070. At some point, we may see a GeForce RTX 4090 Ti with even faster GDDR6X memory.

GDDR7 replaces GDDR6X and promises to reach 32 GHz

It’s still two to three years away, but we already know that GDDR7 memory is in the early stages of development and could be the one powering the successors to the GeForce RTX 40 and Radeon RX 7000, which are scheduled to launch later this year . If no problem occurs, this new standard reaches a frequency of 32 GHzan impressive number that will significantly increase bandwidth.

In case it’s unclear to anyone why bandwidth is so important when talking about graphics cards, I’ll explain in a moment. bandwidth indicates the speed at which the GPU can access the data contained in the graphics memory, which means that the higher it is, the faster the GPU can work. This is why bandwidth reduction can completely cripple a very powerful GPU.

To compare the 32 GHz GDDR7 memory configuration with the 256-bit memory bus it could achieve bandwidth 1 TB/s, while a 16 GHz GDDR6 memory configuration on a 256-bit bus would give us the bandwidth 512 GB/s The difference is very big and we are talking about twice the bandwidth compared to the current generation while maintaining the same bus.