@InProceedings{zhao-EtAl:2026:wmt,
  author    = {Zhao, Jim  and  Maskey, Sohir  and  Oostermeijer, Koen  and  Orr, Douglas  and  Jones, Teryn},
  title     = {Studying quantization trade-offs for efficient inference deployment in machine translation},
  booktitle      = {Proceedings of the Eleventh Conference on Machine Translation},
  month          = {October},
  year           = {2026},
  address        = {Budapest, Hungary},
  publisher      = {Association for Computational Linguistics},
  pages     = {849--866},
  abstract  = {Deploying large language models in realistic server environments poses challenges, as the system needs to provide high-quality responses with low latency. Quantization is a common approach to reduce the memory footprint and improve inference efficiency, yet its impact on latency and throughput is rarely evaluated under controlled, orchestration-level workloads. In this work we study the quantization trade-offs of EuroLLM \citep{martins2025eurollm} across three model sizes ranging from 1.7B to 22B for efficient deployment on a single A100 or H100 GPU. We demonstrate that combining a document-chunking strategy with W4A8 or W8A8 quantization improves the latency-throughput Pareto-curve under a wide range of workloads. Furthermore, since standard machine translation (MT) benchmarks rely on isolated sentences and fail to capture long-context dynamics, we introduce a document-level evaluation based on DocHPLT \cite{o2025dochplt} to assess how text chunking strategies affect translation quality under quantization. Our results indicate that standard segment-level evaluation can potentially underestimate the interaction between quantization and long-context document translation, for some quantization formats, translation direction and models. Overall, our experiments show that the trade-off between inference efficiency and translation quality depends not only on the quantization format, but also on the choice of text chunking strategy.},
  url       = {https://aclanthology.org/2026.wmt-1.46}
}