paper-with-me

홈 › Papers

An Evaluation of LLMs Inference on Popular Single-board Computers

2025-10-20 · Tung, Nguyen, Tuyen Nguyen arxiv

The growing demand for on-device large language model (LLM) inference is driving interest in deploying lightweight, cost-effective AI solutions on edge hardware. Single-board computers (SBCs) such as the Raspberry Pi and Orange Pi offer a promising platform for localized, privacy-preserving inference-but remain underexplored in the context of LLM workloads. In this work, we benchmark the performance of 25 quantized open-source LLMs across three SBCs-Raspberry Pi 4, Raspberry Pi 5, and Orange Pi 5 Pro-using two inference runtimes: Ollama and Llamafile. We evaluate generation throughput, memory usage, and power consumption under varying CPU configurations, using multiple prompt types to simulate realistic workloads. Our results show that SBCs can reliably support models up to 1.5B parameters, with Llamafile achieving up to 4x higher throughput and 30-40% lower power usage than Ollama. We identify architecture-specific bottlenecks, highlight runtime-level trade-offs, and provide practical deployment recommendations. This study offers the first broad evaluation of LLM inference on SBCs, bridging the gap between high-performance language models and affordable edge computing.

📄 PDF Abstract BibTeX arXiv:2511.07425

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Cloud to Edge: Benchmarking LLM Inference On Hardware-Accelerated Single-Board Computers

2026-04-24 · Harri Renney, Fouad Trad, Michael Mattarock, Zena Wood arxiv

Large language models (LLMs) are becoming increasingly capable at small parameter scales. At the same time, conventional cloud-centric deployment introduces challenges around data privacy, latency, and cost that are acut…

AudioBench: A Universal Benchmark for Audio Large Language Models

2024-06-23 · Bin Wang, Xunlong Zou, Geyu Lin, Shuo Sun 외

We introduce AudioBench, a universal benchmark designed to evaluate Audio Large Language Models (AudioLLMs). It encompasses 8 distinct tasks and 26 datasets, among which, 7 are newly proposed datasets. The evaluation tar…

Audio Scene UnderstandingInstruction FollowingScene Understanding

Efficient multi-prompt evaluation of LLMs

2024-05-27 · Felipe Maia Polo, Ronald Xu, Lucas Weber, Mírian Silva 외

Most popular benchmarks for comparing LLMs rely on a limited set of prompt templates, which may not fully capture the LLMs' abilities and can affect the reproducibility of results on leaderboards. Many recent works empir…

MMLU

Correlated Errors in Large Language Models

2025-06-09 · Elliot Kim, Avi Garg, Kenny Peng, Nikhil Garg

Diversity in training data, architecture, and providers is assumed to mitigate homogeneity in LLMs. However, we lack empirical evidence on whether different LLMs differ meaningfully. We conduct a large-scale empirical ev…

Diversity

Boardwalk: Towards a Framework for Creating Board Games with LLMs

2025-08-22 · Álvaro Guglielmin Becker, Gabriel Bauer de Oliveira, Lana Bertoldo Rossato, Anderson Rocha Tavares arxiv

Implementing board games in code can be a time-consuming task. However, Large Language Models (LLMs) have been proven effective at generating code for domain-specific tasks with simple contextual information. We aim to i…

Code Generation