AI Lightweighting & Optimization through Quantization

<div class="se-viewer se-theme-default" lang="ko-KR">
    
    
    
    <div class="se-main-container">
                <div class="se-component se-text se-l-default" id="SE-2b4d23d9-6353-47a4-822e-3ebaf686ee58">
                    <div class="se-component-content">
                        <div class="se-section se-section-text se-l-default">
                            <div class="se-module se-module-text">
                                    <p class="se-text-paragraph se-text-paragraph-align-justify " style="" id="SE-3c4ebfba-2ff2-452e-bd68-18ab8a883142"><span style="color:#000000;" class="se-fs-fs19 se-ff-pretendard  se-style-unset " id="SE-afb34ddf-5651-40c5-8cfe-6d771e24d021">SqueezeBits has developed optimization technology that compresses AI models to below 4-bit precision while preserving performance. Founded by a team with deep R&amp;D experience across AI models and hardware, the company was acquired by AI semiconductor company Rebellions in 2026.</span></p>

                            </div>
                        </div>
                    </div>
                    <script type="text/data" class="__se_module_data" data-module-v2='{"type": "v2_text", "id": "SE-2b4d23d9-6353-47a4-822e-3ebaf686ee58", "data": {"ctype": "text"  }}'></script>
                </div>    </div>
</div>

SqueezeBits has developed optimization technology that compresses AI models to below 4-bit precision while preserving performance. Founded by a team with deep R&D experience across AI models and hardware, the company was acquired by AI semiconductor company Rebellions in 2026.