Skip to main content
Submit
ProceedingsPoster Open access

Benchmarking Sub-Billion-Parameter Models on Commodity Hardware

In Proceedings of the Symposium on Efficient and On-Device Machine Learning (SEODML 2026), pp. 33–34. Singapore, 8 Sep 2026.

DOI 10.xxxx/ctm.pr.2026.0010 · ID CTM-PR-2026-0010

Download PDF

Cite this record

Tanaka, M. & Okafor, D. (2026). Benchmarking Sub-Billion-Parameter Models on Commodity Hardware. In Proceedings of the Symposium on Efficient and On-Device Machine Learning (SEODML 2026) (pp. 33–34). CONTINUUM Proceedings. doi:10.xxxx/ctm.pr.2026.0010

Sample record. Fictional demonstration content.

Abstract

A poster summarising latency, memory and quality for twenty sub-billion-parameter models on a laptop CPU, a single-board computer and a mobile phone.

Keywords benchmarking · small models · hardware

Full text

CTM-PR-2026-0010.pdf

Paper · PDF · pp. 33–34

Download

Demonstration record: no file is attached.

How to cite

Tanaka, M. & Okafor, D. (2026). Benchmarking Sub-Billion-Parameter Models on Commodity Hardware. In Proceedings of the Symposium on Efficient and On-Device Machine Learning (SEODML 2026) (pp. 33–34). CONTINUUM Proceedings. doi:10.xxxx/ctm.pr.2026.0010

More from SEODML 2026