REVIEW 1 cited by
A Performance Evaluation of a Quantized Large Language Model on Various Smartphones
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
This paper explores the feasibility and performance of on-device large language model (LLM) inference on various Apple iPhone models. Amidst the rapid evolution of generative AI, on-device LLMs offer solutions to privacy, security, and connectivity challenges inherent in cloud-based models. Leveraging existing literature on running multi-billion parameter LLMs on resource-limited devices, our study examines the thermal effects and interaction speeds of a high-performing LLM across different smartphone generations. We present real-world performance results, providing insights into on-device inference capabilities.
Forward citations
Cited by 1 Pith paper
-
Medicine on the Edge: Comparative Performance Analysis of On-Device LLMs for Clinical Reasoning
On-device LLMs reach about half the AMEGA clinical-reasoning score of large cloud models, with Med42 and Aloe highest (about 490/1000) and Phi-3 Mini the best accuracy-per-memory trade-off.
Discussion (0). Continue with ORCID to comment.