A report has surfaced overseas confirming that modders have figured out a way to double the RTX 5080's VRAM capacity from 16GB of GDDR7 memory to 32GB. This allows gaming GPUs to be used in workstations and servers, which could ultimately increase their use for AI workloads, potentially creating supply issues. Discovered by Uniko's Hardware (h/t VideoCardz), a Chinese GPU repair technician claims modders are "successfully" modifying RTX 5080s with 32GB of memory, and deploying these mods specifically on RTX 5080 cards boasting blower-style cooler designs that are optimized for workstations and servers.
The modder did not explain how the modification process is being done. Likely, modders are adding eight additional 2GB memory chips to the RTX 5080's PCB to achieve 32GB of capacity. This is something Nvidia does on existing models, such as the RTX Pro 6000 and RTX 5060 Ti 16GB, to reach their respective memory capacities using a clamshell approach.
