Google says running Gemini AI on phones is a huge RAM hog
Last Month, Google said that the running AI models on phones are a huge RAM hog, devices with low RAM will not be able to run its latest AI model, called “Google Gemini.
In March Google made this announcement that out of its latest smartphones only the Pixel 8 and Pixel 8 Pro, would be able to run its latest AI model, called “Google Gemini”. Even the smaller Pixel 8 with similar species would also not be able to run the latest AI model “Gemini”.
Read: Google.org Launches Its New Generative AI Accelerator Program
Google’s Seang Chau, VP of devices and services software, explained on the company’s “Made by Google” podcast. “The Pixel 8 Pro, having 12GB of RAM, was a perfect place for us to put Gemini Nano on the device and see what we could do,” Chau said. “When we looked at the Pixel 8 as an example, the Pixel 8 has 4GB less memory, and it wasn’t as easy of a call to just say, ‘All right, we’re going to enable it on Pixel 8 as well.'” According to Chau, Google’s trepidation is because the company doesn’t want to “degrade the experience” on the smaller Pixel 8, which only has 8GB of RAM.
Further in his Podcast, Chau explained that for some advanced features like “smart reply” smartphones should be RAM-resistant so that they can be loaded 24/7 in your phone. Chau told the podcast, “Smart Reply is something that requires the models to be RAM-resident so that it’s available all the time. You don’t want to wait for the model to load on a Gboard reply, so we keep it resident.”
For all these reasons, Google is keeping the Gemini Nano feature for the developer flag. Until you turn on the developer flag, you will not see Google Gemini ‘smart reply’ on your keyboards. The normal keyboard quick replies are not powered by Google Gemini.
Read: Chrome Launches Native Build for Arm-Powered Windows Laptops
However, if we look, many AI chatbots are in the app now so getting an AI tool that jumps into extra RAM does not sound good. Instead using an app is most preferable. A tool that requires a lot of RAM and can be used for other apps, users will like to keep it off.
