PRESSR: Haltia.AI publishes groundbreaking research on LLM performance on smartphones

First published: 22-Dec-2023 09:11:28

Dubai, UAE – Haltia.AI, a UAE-based AI innovator, has just released a significant academic paper, marking a substantial contribution to the field of artificial intelligence. The study, titled "A Performance Evaluation of a Quantized Large Language Model on Various Smartphones," represents a breakthrough in understanding and optimizing Large Language Models (LLMs) for use on mobile devices.

This research, endorsed and peer-reviewed, evaluates the performance of a specific LLM applied across all iPhone models. It represents a comprehensive and empirical examination of running state-of-the-art LLMs on smartphones, a first of its kind in the AI industry. The study meticulously analyzes factors affecting performance, such as power throttling and thermal effects, providing valuable insights into effective AI processing on portable devices.

As a rising startup, Haltia.AI’s investment in such high-level research underscores its commitment to advancing the AI field. "Our aim is to not only develop innovative products but also contribute meaningfully to the scientific community," said Dr Tolga Çöplü, Head of Research at Haltia.AI.  "This paper showcases our team's ability to conduct significant research, placing us in a league different from most startups in the AI space."

The study's findings are crucial for understanding how to effectively run LLMs on mobile devices, opening up possibilities for AI applications where data privacy, security, and offline functionality are critical. The study indicates that recent iPhone generations can effectively run on-device LLMs, though advancements in power management and system integration are needed to maximize performance.

"We're excited about the implications of this research for the future of AI in everyday life," said Arto Bendiken, CTO and co-founder of Haltia.AI. "Our work demonstrates that advanced AI can be more than just a cloud-based service; it can be personal, private, and accessible anywhere."

Haltia.AI plans to continue its research efforts, and to delve deeper into model compression and acceleration techniques. This ambitious goal highlights the startup’s dedication to being at the forefront of AI innovation and its commitment to contributing to the global AI community.

For media inquiries or to arrange interviews, please contact:

Emma Rymer, Head of Comms Studio, Haltia.AI

Email: emma@haltia.ai

Phone: +44-7979-716804

About Haltia.AI:

Founded by tech visionary and celebrated cypherpunk Arto Bendiken alongside entrepreneurial powerhouse Talal Thabet, Haltia.AI is on a mission to revolutionize industries and enhance quality of life through state-of-the-art AI solutions that prioritize user autonomy and data integrity.  Talal, with 25 years of experience across multiple sectors and five successful exits from eight startups in less than twelve years, pairs seamlessly with Arto's deep tech background to forge a unique leadership synergy that is both innovative and grounded in industry acumen. 

Haltia.AI emerges as a trailblazer in the realm of personal AI, with its pioneering on-device platform built upon the bedrock of cypherpunk principles privacy first.  Haltia.AI's proprietary companions, Halford and Tiana, deliver an unprecedented level of efficiency and privacy in a world demanding ethical technology solutions, enabling the company to fulfil its promise to empower members to "live the life they imagined”.

Headquartered in Delaware, USA and with an operating subsidiary in the United Arab Emirates, the company is bolstered by an elite "dream team" of globally recognized experts and advisors from the realms of cutting-edge engineering to ethical coding. 

© Press Release 2023

Disclaimer: The contents of this press release was provided from an external third party provider. This website is not responsible for, and does not control, such external content. This content is provided on an “as is” and “as available” basis and has not been edited in any way. Neither this website nor our affiliates guarantee the accuracy of or endorse the views or opinions expressed in this press release.

The press release is provided for informational purposes only. The content does not provide tax, legal or investment advice or opinion regarding the suitability, value or profitability of any particular security, portfolio or investment strategy. Neither this website nor our affiliates shall be liable for any errors or inaccuracies in the content, or for any actions taken by you in reliance thereon. You expressly agree that your use of the information within this article is at your sole risk.

To the fullest extent permitted by applicable law, this website, its parent company, its subsidiaries, its affiliates and the respective shareholders, directors, officers, employees, agents, advertisers, content providers and licensors will not be liable (jointly or severally) to you for any direct, indirect, consequential, special, incidental, punitive or exemplary damages, including without limitation, lost profits, lost savings and lost revenues, whether in negligence, tort, contract or any other theory of liability, even if the parties have been advised of the possibility or could have foreseen any such damages.