Google sets high hardware requirements for Gemini Intelligence. (Image: Google). Google’s AI generation Gemini Intelligence has high hardware requirements and may not even land on the Pixel 9 Pro and many other smartphones. Already during the announcement of Gemini Intelligence [1] at the Android Show I/O Edition, Google hinted with the statement “The best of Gemini on our most advanced devices” that the on-device AI would have high requirements for devices. Google left concrete details in the footnotes: According to these, the Pixel 9 series and even the Galaxy Z Fold 7 from last year are out of the running – apparently even the Xiaomi 17 Ultra.
“Highest performance and system requirements”. “Gemini Intelligence features are only available on Android devices that meet the highest performance and system requirements,” Google writes in footnote [2] and specifies for RAM that devices must have at least 12 GB of memory installed. This already rules out most entry-level and mid-range devices; even Google’s own a-series, which is equipped with 8 GB of RAM, cannot run Gemini Intelligence.
Another hurdle is the processor: Google only writes here “qualified SOC” and in parentheses “flagship chip”. The manufacturer is likely referring to Qualcomm and MediaTek’s top models – as well as their own Tensor chips of the current and upcoming generation.
But that’s not all: Google also sets the bar high regarding the required on-device AI version: It must support at least Gemini Nano v3 or newer. This is where even the more powerful models separate the wheat from the chaff: On Google’s developer website for GenAI APIs of ML Kit, Google lists which devices are compatible with v3 and which remain on the older version 2.
Only smartphones from 2025 and newer are compatible with Gemini Nano v3 – this means, among other things, that Google’s Pixel 9 series, Honor’s Magic V5, Magic 7 and Magic 7 Pro, as well as the OnePlus 13 and others are ruled out. But devices from last year and even state-of-the-art devices are also not compatible with Gemini Intelligence according to the list: For example, Samsung’s Galaxy Z Fold 7 as well as 2026 devices Xiaomi 17 and 17 Ultra and a whole range of other Xiaomi models are unable to run Gemini Intelligence.
Update guarantee, secure virtualization. Apart from hardware and software requirements, Google makes clear specifications for Gemini Intelligence regarding updates: If manufacturers want to use the new AI on their devices, they must guarantee at least 5 years of Android updates and six years of quarterly security patches.
Furthermore, Google requires companies to use virtualization technologies announced last year [3] pKVM (protected Kernel-based Virtual Machine) to secure the data processed by the AI. These are intended to ensure that information is processed only locally and that unauthorized apps have no direct access.
An advantage of Gemini Intelligence, by the way, is that tasks are executed directly on the device rather than in the cloud, which is a plus in terms of privacy. Those who don’t want to use AI don’t have to: like the previous Gemini Assistant, Gemini Intelligence is likely to remain optional.
(afl [5]). URL of this article:. https://www.heise.de/-11296835. Links in this article:. https://www.heise.de/news/Google-stellt-Gemini-Intelligence-fuer-Android-vor-11289291.html. https://www.android.com/gemini-intelligence/#:~:text=1%20Gemini%20Intelligence%20features%20are%20only%20available%20on%20Android%20devices%20with%20the%20most%20advanced%20capabilities%20and%20spec%20requirements%3A. https://blog.google/security/android-pkvm-certified-sesip-level-5/. https://www.heise.de/newsletter/anmeldung.html?id=ki-update&wt_mc=intern.red.ho.ho_nl_ki.ho.markenbanner.markenbanner. mailto:afl@heise.de. Copyright © 2026 Heise Medien
heise security News