SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments

TL;DR

Shakti is a 2.5 billion parameter language model optimized for edge devices, offering high performance and efficiency for real-time NLP tasks in resource-limited environments, including support for vernacular languages.

Contribution

The paper introduces Shakti, a compact yet powerful language model designed specifically for edge AI, combining high accuracy with low resource consumption.

Findings

Performs competitively against larger models on benchmarks.

Maintains low latency and high efficiency on edge devices.

Supports vernacular languages and domain-specific tasks.

Abstract

We introduce Shakti, a 2.5 billion parameter language model specifically optimized for resource-constrained environments such as edge devices, including smartphones, wearables, and IoT systems. Shakti combines high-performance NLP with optimized efficiency and precision, making it ideal for real-time AI applications where computational resources and memory are limited. With support for vernacular languages and domain-specific tasks, Shakti excels in industries such as healthcare, finance, and customer service. Benchmark evaluations demonstrate that Shakti performs competitively against larger models while maintaining low latency and on-device efficiency, positioning it as a leading solution for edge AI.