LLMPi: Optimizing LLMs for High-Throughput on Raspberry Pi

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ardakani, Mahsa, Malekar, Jinendra, Zand, Ramtin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916672536838144
author Ardakani, Mahsa
Malekar, Jinendra
Zand, Ramtin
author_facet Ardakani, Mahsa
Malekar, Jinendra
Zand, Ramtin
contents Deploying Large Language Models (LLMs) on resource-constrained edge devices like the Raspberry Pi presents challenges in computational efficiency, power consumption, and response latency. This paper explores quantization-based optimization techniques to enable high-throughput, energy-efficient execution of LLMs on low-power embedded systems. Our approach leverages k-quantization, a Post-Training Quantization (PTQ) method designed for different bit-widths, enabling efficient 2-bit, 4-bit, 6-bit, and 8-bit weight quantization. Additionally, we employ ternary quantization using Quantization-Aware Training (QAT) for BitNet models, allowing for more effective adaptation to lower-bit representations while preserving accuracy. Our findings highlight the potential of quantized LLMs for real-time conversational AI on edge devices, paving the way for low-power, high-efficiency AI deployment in mobile and embedded applications. This study demonstrates that aggressive quantization strategies can significantly reduce energy consumption while maintaining inference quality, making LLMs practical for resource-limited environments.
format Preprint
id arxiv_https___arxiv_org_abs_2504_02118
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLMPi: Optimizing LLMs for High-Throughput on Raspberry Pi
Ardakani, Mahsa
Malekar, Jinendra
Zand, Ramtin
Machine Learning
Artificial Intelligence
Deploying Large Language Models (LLMs) on resource-constrained edge devices like the Raspberry Pi presents challenges in computational efficiency, power consumption, and response latency. This paper explores quantization-based optimization techniques to enable high-throughput, energy-efficient execution of LLMs on low-power embedded systems. Our approach leverages k-quantization, a Post-Training Quantization (PTQ) method designed for different bit-widths, enabling efficient 2-bit, 4-bit, 6-bit, and 8-bit weight quantization. Additionally, we employ ternary quantization using Quantization-Aware Training (QAT) for BitNet models, allowing for more effective adaptation to lower-bit representations while preserving accuracy. Our findings highlight the potential of quantized LLMs for real-time conversational AI on edge devices, paving the way for low-power, high-efficiency AI deployment in mobile and embedded applications. This study demonstrates that aggressive quantization strategies can significantly reduce energy consumption while maintaining inference quality, making LLMs practical for resource-limited environments.
title LLMPi: Optimizing LLMs for High-Throughput on Raspberry Pi
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2504.02118