<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="suman-bentivogli-2026-fbks">
    <titleInfo>
        <title>FBK’s Submission to WMT26 Model Compression Task: Improving Inference Speed for Quantized Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dhairya</namePart>
        <namePart type="family">Suman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Luisa</namePart>
        <namePart type="family">Bentivogli</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Eleventh Conference on Machine Translation</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Barry</namePart>
            <namePart type="family">Haddow</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tom</namePart>
            <namePart type="family">Kocmi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Philipp</namePart>
            <namePart type="family">Koehn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christof</namePart>
            <namePart type="family">Monz</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-474-3</identifier>
    </relatedItem>
    <abstract>This paper presents FBK’s submission to the WMT26 Shared Task on Model Compression. The task requires compressing the Gemma 3 12B model for machine translation on the Czech-German language pair under the task’s constrained track. Post-training quantization (PTQ) methods such as GPTQ have become an industry standard for model compression, but in their standard, weight-only form they reduce only the on-disk size of the model; leaving the activations are in full-precision. As part of this submission, we quantize both weights and activations to 8-bits (W8A8), aiming to also improve inference speed in addition to memory savings, while preserving translation quality. We submit two systems: both quantizing activations d using round-to-nearest quantization, one of which additionally applies SmoothQuant’s channel-wise smoothing before quantization. Our experiments demonstrate that both the W8A8 systems increase throughput by more than 20% while only slightly reducing in quality relative to the full precision model.</abstract>
    <identifier type="citekey">suman-bentivogli-2026-fbks</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.144/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>2061</start>
            <end>2066</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T FBK’s Submission to WMT26 Model Compression Task: Improving Inference Speed for Quantized Models
%A Suman, Dhairya
%A Bentivogli, Luisa
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Eleventh Conference on Machine Translation
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-474-3
%F suman-bentivogli-2026-fbks
%X This paper presents FBK’s submission to the WMT26 Shared Task on Model Compression. The task requires compressing the Gemma 3 12B model for machine translation on the Czech-German language pair under the task’s constrained track. Post-training quantization (PTQ) methods such as GPTQ have become an industry standard for model compression, but in their standard, weight-only form they reduce only the on-disk size of the model; leaving the activations are in full-precision. As part of this submission, we quantize both weights and activations to 8-bits (W8A8), aiming to also improve inference speed in addition to memory savings, while preserving translation quality. We submit two systems: both quantizing activations d using round-to-nearest quantization, one of which additionally applies SmoothQuant’s channel-wise smoothing before quantization. Our experiments demonstrate that both the W8A8 systems increase throughput by more than 20% while only slightly reducing in quality relative to the full precision model.
%U https://aclanthology.org/2026.wmt-main.144/
%P 2061-2066

Markdown (Informal)

[FBK’s Submission to WMT26 Model Compression Task: Improving Inference Speed for Quantized Models](https://aclanthology.org/2026.wmt-main.144/) (Suman & Bentivogli, WMT 2026)

• FBK’s Submission to WMT26 Model Compression Task: Improving Inference Speed for Quantized Models (Suman & Bentivogli, WMT 2026)

ACL

• Dhairya Suman and Luisa Bentivogli. 2026. FBK’s Submission to WMT26 Model Compression Task: Improving Inference Speed for Quantized Models. In Proceedings of the Eleventh Conference on Machine Translation, pages 2061–2066, Budapest, Hungary. Association for Computational Linguistics.