Nvidia is apparently preparing a significant update to its line of laptop GPUs. The upcoming RTX 50 series, codenamed “GN22,” will feature six different variants, surpassing the five options offered in the current RTX 40 series, according to an apparent leak shared by security researcher Dominic Alvieri.
If true, the most notable improvement in the updated specs is the increase in video random access memory (VRAM). The base for the RTX 50 series will be 8GB of VRAM, a step forward compared to the base 6GB that its GPUs come with in current laptops.
The lineup will include three models with 8GB of VRAM, two with a solid 16GB and one with 12GB, according to reports.
This increase in VRAM will allow the new GPUs to run more artificial intelligence (AI) models, which often require substantial memory resources. For example, Stable Diffusion 1.5 requires at least 4GB of VRAM to function properly. SDXL requires at least 6GB to run.
When Stability AI introduced its upcoming SD3 model, which will be much more capable and powerful, it used GPUs with 24GB of VRAM. Fortunately, different versions will be available, with 800 million to 8 billion parameters, and different configurations, such as excluding your T5 text encoder from 4.7 billion parameters, will not be as demanding.
According to the leak, the RTX 50 series will also take advantage of faster GDDR7 memory, further improving the performance of AI and gaming-related tasks.
The leaked roadmap suggests that Nvidia plans to continue producing some older GPUs, such as the RTX 4050 and RTX 3050, with 4GB and 6GB of VRAM to meet the market’s need for cheaper hardware. For gaming, 6GB cards are still solid options, as VRAM is not as important as clock speeds and number of processors or cores.
According to the report, these GPUs will be launched in 2025, although no specific timeline was provided. There have been conflicting rumors, but it is possible that it will be presented at CES 2025.
Buyers looking for cheap cards may have their days numbered. Taiwan Semiconductor Manufacturing Company (TSMC), Nvidia’s main chip supplier, is said to be considering a price increase as its own expenses grow.
“We hope our customers will share some of the higher cost with us, and we have already started our discussion with our customers,” Wei said, according to Nikkei Asia.
The report said Wei recently referred to Nvidia CEO Jensen Huang as the “three trillion guy,” referencing Nvidia’s soaring market value, which surpassed $3 trillion last week.
TSMC produces approximately 90% of the world’s most advanced processor chips and is a vital player in Nvidia’s success.
Despite the potential for rising production costs, Huang expressed support for TSMC’s arguments, saying that raising prices is “consistent with the value they offer,” as reported. Nikkei Asia.
Morgan Stanley analysts have suggested that if Nvidia accepts a price increase from TSMC, other key AI players may follow and raise their prices. They estimate that Nvidia will represent 10% of TSMC’s revenue this year.
