# English K_Quantization of LLMs Does Not Disproportionately Diminish Multilingual Performance

arXiv: https://arxiv.org/abs/2503.03592 · HTML: https://mlsanity.com/paper/2503.03592/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 5 Mar 2025.

## Builds on (most cited first, 10 of 10)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [How do Large Language Models Handle Multilingualism?](https://mlsanity.com/paper/2402.18815/) (2024)
- [MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures](https://mlsanity.com/paper/2406.06565/) (2024)
- [How Does Quantization Affect Multilingual LLMs?](https://mlsanity.com/paper/2407.03211/) (2024)
- [Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages](https://mlsanity.com/paper/2404.11553/) (2024)
- [Operationalizing a National Digital Library: The Case for a Norwegian Transformer Model](https://mlsanity.com/paper/2104.09617/) (2021)
- [Large-Scale Contextualised Language Modelling for Norwegian](https://mlsanity.com/paper/2104.06546/) (2021)

## Built on by (most cited first, 1 of 1)

- [A Calibrated Instrument for Measuring How Inference Optimizations Affect Output Quality](https://mlsanity.com/paper/2609.18005/) (2026)

## Abstract (arXiv)

For consumer usage of locally deployed LLMs, the GGUF format and kquantization are invaluable tools for maintaining the performance of the original model while reducing it to sizes deployable with consumer-grade hardware. The number of bits dedicated to each weight from the original model is reduced based on how important they are thought to be during model inference. This importance is arrived at through the application of an 'importance matrix'-a relatively small text document meant to be representative of the LLM's standard use-cases. In the vast majority of quants available online, this document is primarily written in English. It was therefore an open question whether performance on English language tasks was preserved through the sacrifice of multilingual performance and whether it can be preserved with alternate importance matrices. This article investigates these hypotheses by quantizing Llama3.3 70B on importance matrices written in three languages (English, Norwegian, and Malayalam) and evaluating them on the MixEval dataset in both English and Norwegian. All experiments related to yielded non-significant results indicating that current quantization practices do not disproportionately harm multilingual performance.