Groundbreaking iPhone App Runs Optimized GPT AI Models Entirely Offline and On-Device, for a Greener, More Private Alternative to Data Centre Driven Products.

N6, an independent British software developer, has released LiberaGPT, a free iPhone app that runs multiple GPT models ...

Google’s new Gemma 4 models bring complex reasoning skills to low-power devices

Built on the same architectural foundation as Gemini 3, the models are designed to handle complex reasoning tasks and support ...

Google's Gemma 4 Open Models Target On-Device AI From Phones To GPUs

Gemma is Google's series of open-weights models, which means you can download them and run them on your own hardware.

Google launches Gemma 4, a new open-source model: How to try it

Google just released the latest version of its open AI model, Gemma 4, on Thursday. Crucially, Gemma 4 is a fully open-source ...
The Next Web

Google launches Gemma 4: four open-weight models from smartphones to workstations

Google has launched Gemma 4, four open-weight models from E2B edge to 31B Dense, built from Gemini 3 research, released under ...
Hosted on MSN

Apple’s AI gets smarter with live translation, on-device models, and developer tools

Apple’s next big leap in AI is here. Seamlessly integrated across iPhone, Mac, and even Watch, Apple Intelligence now lets your devices talk, translate, and create like never before. Announced at ...
TweakTown

The iPhone 17 Pro can run a 400B parameter Large Language Model on-device by streaming weights from the SSD

While the speed remains impractical for daily use, this proof of concept demonstrates how new inference engines are ...
MacRumors

Apple Announces Foundation Models Framework for Developers to Leverage AI

Apple at WWDC today announced Foundation Models Framework, a new API allowing third-party developers to leverage the large language models at the heart of Apple Intelligence and build it into their ...