Whether you’re a gamer trying to play the latest AAA games at high resolutions and max settings, or an AI enthusiast trying to run models locally, we’ve reached the point where a GPU with 8GB of video memory is a pretty limiting bottleneck. But with ongoing memory shortages and price hikes, it’s a unique time for GPU manufacturers to try to solve this problem—rumours Nvidia’s mid-generation “Super” update, which increased RAM for its RTX 50 series GPUs, was quietly delayed or canceled earlier this year, at least in part due to memory costs.
One of Nvidia’s GPUs does to get a RAM upgrade, according to an announcement the company buried below a blog post about regular Game Ready driver update. The notebook version of the GeForce RTX 5070 gets an increase from 8GB to 12GB of GDDR7, a 50 percent increase that should alleviate some of the performance bottlenecks and future-proofing of the GPU in general.
Otherwise, the 12GB version of the mobile RTX 5070 is identical to the 8GB version. The RAM is still connected to the GPU via a 128-bit memory interface, and the GPU still has 4,608 CUDA cores. The mobile 5070 uses the same GB206 silicon die as the desktop RTX 5060 instead of the larger, more powerful GB205 die in the desktop version of the RTX 5070, meaning that despite the RAM increase, the desktop version remains the more powerful GPU.
