British Software Company Achieves Pioneering Breakthrough, Making It Possible to Now Run a 24 Billion Parameter AI Large Language Model Entirely Offline on the iPhone

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.
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.

The update follows a strong first month for LiberaGPT, which has already attracted thousands of users around the world. Rapid adoption and encouraging feedback indicate a clear appetite for AI tools that offer both capability and privacy in a fully local environment.

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.

The comparison with earlier generations of AI highlights the scale of that advance. OpenAI's GPT-2, introduced in 2019, was widely recognised as a landmark model, yet it operated at 1.5 billion parameters and depended heavily on centralised infrastructure. Since then, major gains in efficiency and model design have reshaped expectations, allowing more powerful systems to operate without the same computational burden.

Alongside the new 24 billion-parameter model, the latest LiberaGPT release also includes a range of smaller models for users who prefer faster performance and lower resource use. Together, these options give users the flexibility to choose the balance of speed and capability that suits them best, while keeping the entire experience private and on-device.

What matters here is not only the size of the model, but the fact that it runs at all on consumer mobile hardware. Models in this class have usually belonged to server infrastructure or desktop systems. This small independent software house has brought that level of capability to the iPhone through careful optimisation and precise memory management.

Capable local GPU processing gives users more privacy, faster response times, and the ability to use advanced AI models without dependence on a network connection or contribution to AI data centre infrastructure for daily routine tasks.

LiberaGPT's Audition mode lets users send a single prompt to every installed model on their device, all at once, for side-by-side comparison, with seven models available at the time of publication. An advanced info display also surfaces real-time token generation rate, thermal state, and memory usage. Every one of these features runs locally with no cloud dependency, consistent with the offline-first philosophy of the app itself.

Stephen J. Pereira, Lead Developer of the project, said: "Our software is a bit like a cassette player for optimised AI models, with the different available LLMs considered a collection of cassettes. With the rapid pace at which leaner, more highly optimised models are being released, we see an opportunity to embrace their diversity of strengths. Rather than relying on a monolithic cloud system, users can load one of many more specialised smaller models privately and locally, in a far more energy-efficient way. The user's unique ideas and concepts remain their own and aren't made available to improve LLM knowledge for a wider audience."

For this small software firm, the pioneering update signals a clear shift in direction. Instead of sending mundane questions or tasks to distant data centres, LiberaGPT offers a greener alternative, using modern personal GPUs alongside smarter software algorithms to handle a substantial portion of everyday requests locally.

Beyond the technical details, the real focus is the user experience. The app introduces a clean, minimalist, user-friendly experience built around privacy, offline functionality, and more efficient use of computing power. For everyday, simpler tasks, it delivers results comparable to cloud-based LLMs like OpenAI's ChatGPT, Google's Gemini, and Anthropic's Claude, without subscription costs or data centre reliance.

LiberaGPT is available as a free download on the iOS App Store:

https://apps.apple.com/app/liberagpt/id6761083160

http://www.liberagpt.com

http://www.5N6.co.uk

Media Contact
Company Name: 5N6 LTD
Contact Person: Amy J. Waller
Email:Send Email [https://www.abnewswire.com/email_contact_us.php?pr=british-software-company-achieves-pioneering-breakthrough-making-it-possible-to-now-run-a-24-billion-parameter-ai-large-language-model-entirely-offline-on-the-iphone]
Address:5 Tivoli House Wigmore Park Centre
State: Bedfordshire
Country: United Kingdom
Website: http://www.5N6.co.uk

Legal Disclaimer: Information contained on this page is provided by an independent third-party content provider. ABNewswire makes no warranties or responsibility or liability for the accuracy, content, images, videos, licenses, completeness, legality, or reliability of the information contained in this article. If you are affiliated with this article or have any complaints or copyright issues related to this article and would like it to be removed, please contact retract@swscontact.com



This release was published on openPR.