# An Evaluation of LLMs Inference on Popular Single-board Computers

arXiv: https://arxiv.org/abs/2511.07425 · HTML: https://mlsanity.com/paper/2511.07425/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 20 Oct 2025.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model](https://mlsanity.com/paper/2502.02737/) (2025)
- [From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference](https://mlsanity.com/paper/2310.03003/) (2023)
- [Trustworthiness in Retrieval-Augmented Generation Systems: A Survey](https://mlsanity.com/paper/2409.10102/) (2024)
- [LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models](https://mlsanity.com/paper/2309.14393/) (2023)
- [Norm Tweaking: High-performance Low-bit Quantization of Large Language Models](https://mlsanity.com/paper/2309.02784/) (2023)
- [Hybrid Heterogeneous Clusters Can Lower the Energy Consumption of LLM Inference Workloads](https://mlsanity.com/paper/2407.00010/) (2024)
- [Text vectorization via transformer-based language models and n-gram perplexities](https://mlsanity.com/paper/2307.09255/) (2023)
- [Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation](https://mlsanity.com/paper/2411.03957/) (2024)

## Abstract (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.