LLM INFERENCE PERFORMANCE ANALYSIS ACROSS WINDOWS, WINDOWS SUBSYSTEM FOR LINUX 2 AND NATIVE LINUX

Anshori, Muhammad and Anshori, Muhammad (2026) LLM INFERENCE PERFORMANCE ANALYSIS ACROSS WINDOWS, WINDOWS SUBSYSTEM FOR LINUX 2 AND NATIVE LINUX. LLM INFERENCE PERFORMANCE ANALYSIS ACROSS WINDOWS, WINDOWS SUBSYSTEM FOR LINUX 2 AND NATIVE LINUX, 12 (1). pp. 451-462. ISSN 2527-4864

Text 39_8435_Production.pdf Restricted to Registered users only Download (755kB) | Request a copy

Abstract

The increasing use of Large Language Models (LLMs) on consumer devices raises practical
concerns regarding inference latency and resource efficiency, which can vary depending on the operating
system environment. However, it is still unknown which operating system is most optimal and efficient for
executing local LLM workloads on hardware with limited resources. Therefore, this study aims to compare and
evaluate the inference performance of LLMs across three operating system environments: native Windows,
Windows Subsystem for Linux 2 (WSL2), and native Linux on a low-spec laptop equipped with a 12th Gen Intel
Core i3 processor and 8 GB of RAM. The Ollama framework is used to run several lightweight LLM models,
including Llama3.2:3B, Qwen2.5:3B, and Phi3.5:3.8B. An experimental benchmarking approach is conducted
using three levels of prompt complexity (light, medium, and heavy), with 10 trials for each prompt scenario to
ensure consistency of results. Evaluation metrics include inference latency, CPU utilization, and memory
consumption during model execution. Results show that the operating system environment significantly
impacts the inference performance of LLMs. For example, using the Llama3.2:3B model under heavy
prompting, the average latency reaches 71.24 seconds on Windows, 75.96 seconds on WSL2, and 70.80 seconds
on native Linux, while under light prompting the average latency is 11.76 seconds, 12.73 seconds, and 10.83
seconds, respectively. These findings indicate that native Linux generally provides more efficient LLM inference
on resource-constrained hardware. This study contributes an empirical and repeatable comparison across
operating system environments, providing practical insights for selecting deployment platforms for LLM
applications.

Item Type:	Article
Uncontrolled Keywords:	Benchmarking, LLM Inference, Linux, Windows, WSL2.
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4050 Electronic information resources
Divisions:	Fakultas Teknik > S1 Teknologi Informasi
Depositing User:	Unnamed user with email [email protected]
Date Deposited:	03 Nov 2026 01:56
Last Modified:	03 Nov 2026 01:56
URI:	https://repository.unuja.ac.id/id/eprint/5580

Actions (login required)

View Item