Metraipolis › archive › dc_6525deb3daf4

Quantization Effects on Bangla Language Understanding in Large Language Models: A Systematic Evaluation — arXiv:2608.24615

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.24615
License (as archived)
CC0-1.0
Archived
2026-10-18T06:18:08.953Z
SHA-256 of the archived text
fd2759d4c69e3801b2b9c6434e31fc84eda7882dcacc18f50b3a60f41deefe82
Stable URL of this page
https://metraipolis.com/documento/dc_6525deb3daf4

How to cite

Quantization Effects on Bangla Language Understanding in Large Language Models: A Systematic Evaluation — arXiv:2608.24615 — arXiv (en), https://arxiv.org/abs/2608.24615 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6525deb3daf4 (Metraipolis archive dc_6525deb3daf4, sha256 fd2759d4c69e3801b2b9c6434e31fc84eda7882dcacc18f50b3a60f41deefe82)
BibTeX
@misc{dc6525deb3daf4,
  title = {Quantization Effects on Bangla Language Understanding in Large Language Models: A Systematic Evaluation — arXiv:2608.24615},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.24615},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6525deb3daf4; sha256 fd2759d4c69e3801b2b9c6434e31fc84eda7882dcacc18f50b3a60f41deefe82},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.24615. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Post-training quantization lowers the memory footprint of Large Language Models (LLMs) and speeds up inference, which is why it is now common for on-device deployment. Most of what we know about its effects, however, comes from English benchmarks. It is not clear whether the same holds for morphologically complex, low-resource languages such as Bangla, and this gap is what we address here. We evaluate three model families---Qwen-2.5-7B, LLaMA-3.1-8B, and GPT-OSS-20B---in full precision and in three quantized formats (GPTQ-Int8, GPTQ-Q8, GGUF-W8A16) across five Bangla natural language understanding benchmarks (Bangla MMLU, CommonsenseQA-BN, OpenBookQA-BN, PIQA-BN, and BoolQ-BN), using zero-shot evaluation through lm-evaluation-harness. To our knowledge this is the first controlled comparison of quantization formats on Bangla NLU. The three families do not respond the same way: GPT-OSS loses up to 57.35% accuracy on reasoning-heavy tasks under GGUF-W8A16, while Qwen and LLaMA hold steady under GPTQ, and in a few cases the quantized version edges out the full-precision one. BoolQ-BN, a comprehension task, stays stable across all three families regardless of format. Taken together, these results suggest quantization can work well for Bangla deployment, but the choice of architecture and quantization method matters more than the bit width alone. We discuss what this means for practitioners choosing a model to run on constrained hardware.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.24615 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T06:17:29.372Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).