プレス

When British developer 5N6 released LiberaGPT on March 30, the unveiling felt less like a product launch and more like a milestone in the history of personal computing. For the first time, an iPhone could host multiple GPT‑style language models that run entirely on the handset, without ever reaching for the distant servers that have dominated AI delivery for the past decade. The significance of this development goes beyond the novelty of offline chat; it reshapes expectations around privacy, ene

Bedfordshire, UK - April 21, 2026 - Independent British software house 5N6 today unveiled a major update to LiberaGPT, its recently launched iPhone app, adding support for a record-breaking 24 billion-parameter large language model that runs entirely offline on the latest generation of iPhone devices, with complete privacy and no requirement for cloud data centres or additional hardware.

"Until recently, the idea of running a model of this size privately on a smartphone would have been regarded as technically out of reach for current flagship handsets. LiberaGPT now brings that capability to iPhone, ensuring that prompts and responses remain entirely on the device." Privacy focused iPhone app...

Privacy focused iPhone app LiberaGPT has been updated to now support the largest and most intelligent AI model ever to run entirely offline on an unmodified iPhone.

Independent British software house 5N6 has unveiled a major update to LiberaGPT, its recently launched iPhone app, adding support for a record-breaking 24 billion-parameter large language model that runs entirely offline on the latest generation of iPhone devices, with complete privacy and no requirement for cloud data centres or additional hardware.

“We wanted users of the app to be free from subscription costs while also providing a productivity tool with a substantially reduced environmental footprint.”

“For many everyday AI requests, the smartphone no longer has to be just a remote screen to display the output of external computation.”