Large Language Models on Small Resource-Constrained Systems: Performance Characterization, Analysis and Trade-offs
This work addresses the need for running LLMs locally on edge devices for privacy, security, and network independence, offering a baseline for recent hardware but is incremental as it builds on existing optimization research.
The research characterized the performance of large language models (LLMs) on recent NVIDIA Jetson Orin embedded hardware, using models from 70 million to 1.4 billion parameters, and provided a utility for batch testing to analyze trade-offs and optimization choices.
Generative AI like the Large Language Models (LLMs) has become more available for the general consumer in recent years. Publicly available services, e.g., ChatGPT, perform token generation on networked cloud server hardware, effectively removing the hardware entry cost for end users. However, the reliance on network access for these services, privacy and security risks involved, and sometimes the needs of the application make it necessary to run LLMs locally on edge devices. A significant amount of research has been done on optimization of LLMs and other transformer-based models on non-networked, resource-constrained devices, but they typically target older hardware. Our research intends to provide a 'baseline' characterization of more recent commercially available embedded hardware for LLMs, and to provide a simple utility to facilitate batch testing LLMs on recent Jetson hardware. We focus on the latest line of NVIDIA Jetson devices (Jetson Orin), and a set of publicly available LLMs (Pythia) ranging between 70 million and 1.4 billion parameters. Through detailed experimental evaluation with varying software and hardware parameters, we showcase trade-off spaces and optimization choices. Additionally, we design our testing structure to facilitate further research that involves performing batch LLM testing on Jetson hardware.