SQ-LoRA: Memory-Efficient Language Model Compression Through Stable-Rank-Guided Quantization for Edge Computing Applications

Seda Bayat Toksöz, Gültekin Işik

Open source

DOI
10.3390/app16042113
Published
2026-02-21
Container
Applied Sciences
Publisher
MDPI AG
Open access
unknown

Credibility signals

uncertain Score 64/100 under policy 1.0.0. This is a metadata assessment, not a judgment of the paper's conclusions.

Show all credibility signals

Cite this work

BibTeX

@article{allodium:10.3390/app16042113,
  title = {SQ-LoRA: Memory-Efficient Language Model Compression Through Stable-Rank-Guided Quantization for Edge Computing Applications},
  author = {Seda Bayat Toksöz and Gültekin Işik},
  year = {2026},
  journal = {Applied Sciences},
  doi = {10.3390/app16042113},
  url = {https://doi.org/10.3390/app16042113}
}

RIS

TY  - JOUR
TI  - SQ-LoRA: Memory-Efficient Language Model Compression Through Stable-Rank-Guided Quantization for Edge Computing Applications
AU  - Seda Bayat Toksöz
AU  - Gültekin Işik
PY  - 2026
JO  - Applied Sciences
DO  - 10.3390/app16042113
UR  - https://doi.org/10.3390/app16042113
ER  - 

APA

Toksöz, S. B., & Işik, G. (2026). SQ-LoRA: Memory-Efficient Language Model Compression Through Stable-Rank-Guided Quantization for Edge Computing Applications. Applied Sciences. https://doi.org/10.3390/app16042113

Source records