Liquid AI revolutionizes LLM to work on edge devices, such as smartphones with the up-to-date “Edge Hyena” model

Yesterday the company announced “Edge hyena“A up-to-date model based on fitness, a multi -synar model designed for smartphones and other edge devices before International conference on the learning representation (ICLR) 2025.

The conference, one of the most significant events in the field of machine research, will take place this year in Vienna in Austria.

The up-to-date model based on the weave promises faster, more saving AI on the edge

Hyena Edge is designed to elevate robust basic transformers base lines for both computing performance and the quality of the language model.

In real tests on the Samsung Galaxy S24 Ultra smartphone, the model provided a lower delay, less memory trace and better comparative results compared to the transformer model tailored to the parameters.

Novel architecture of the up-to-date era Edge AI

Unlike most tiny models designed for mobile implementation-in this SMOLLM2, Phi Models and Llam 3.2 1B-Hiena Edge departs from customary projects. Instead, it strategically replaces two-thirds of the grouped (GQA) remarks with closed with the hyena-y family.

The up-to-date architecture is the result of a liquid synthesis of AI architecture framework (Star), which uses evolutionary algorithms for automatic design of the model’s spine and was announced in December 2024.

Star examines a wide range of operator composition, rooted in mathematical theory of linear input changing systems, in order to optimize in terms of many specifics specific to equipment, such as delay, memory and quality.

Benchmarked directly on consumer equipment

To confirm that Hyen Edge Edge’s readiness, liquid artificial intelligence conducted tests directly on the Samsung Galaxy S24 smartphone.

The results show that the Edge hyena achieved up to 30% faster congestion and decoding of delays compared to its equivalent Transformer ++, with speed advantages increased at longer sequence lengths.

Pre-filling delays at brief sequence lengths also overtook the base line of the transformer-curitic performance record for responsive applications on the device.

In terms of memory, Hiene Edge consistently used less RAM during the application in all tested sequence lengths, setting it as a robust candidate for environments with strict resource restrictions.

Exceeding transformers in the field of comparative tests

Hyena Edge has been trained for 100 billion tokens and assessed in standard comparative tests for tiny language models, including Wikitext, Lambada, Piqa, Hellaswag, Winogrande, Arc-Basic and Arc-Challenge.

At any reference point, Hyen Edge either matched or exceeded the performance of the GQA-Transformer ++ model, with a noticeable improvement in the results of embarrassment on Wikitext and Lambada and a higher accuracy indicator for PIQA, Hellaswag and Winogrande.

These results suggest that the enhance in the performance of the model does not result from the costs of the predictive quality-the support for many architectures optimized by the edges.

HIENE EDGE EVOLUTION: Looking at performance trends and operator

For those who are looking for a deeper immersion in the Hyena Edge development process, recently Video fight Provides a convincing visual summary of the model’s evolution.

The film emphasizes how key performance indicators – including preliminary delay, delaying decoding and memory consumption – improved compared to subsequent generations of architecture improvement.

It also offers a infrequent behind -the -scene look at how the internal composition of the hyena edge during development has moved. Viewers can see vigorous changes in the arrangement of operators, such as self -improvement mechanisms (SA), various variants of hyenas and sigl layers.

These changes offer insight into the principles of architectural design, which helped the model achieve its current level of performance and accuracy.

By visualizing the compromises and dynamics of the operator in time, the video is a valuable context for understanding the architectural breakthroughs underlying Hyen Edge’s performance.

Open Source plans and a wider vision

Hyena Edge’s debut also emphasizes the growing potential of alternative architecture to question transformers in practical settings. Because mobile devices will more and more often operate natively sophisticated loads of artificial intelligence, models such as HYENA Edge can set a up-to-date base line for what AI optimized by EDGE can achieve.

Hyena Edge’s success – both in raw performance indicators and in the presentation of automated architectural design – positions liquid artificial intelligence as one of the emerging players to observe in the evolving landscape of the AI ​​model.

Daily observations in matters of business employ with VB daily

If you want to impress your boss, VB Daily is covered by you. We give you an internal measure about what companies do with generative artificial intelligence, from regulatory changes to practical implementation, so you can share insights for the maximum roi.

Read our Privacy Policy

Thanks for the subscription. Check out more VB newsletter here.

There was a mistake.