# MoBiE: Efficient Inference of Mixture of Binary Experts under Post-Training Quantization

arXiv: https://arxiv.org/abs/2604.06798 · HTML: https://mlsanity.com/paper/2604.06798/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in MoE large language models, one of 12 directions in Mixture-of-experts.
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Placed in

- Mixture-of-experts / [MoE large language models](https://mlsanity.com/moe/moe-large-language-models/)

## Builds on (most cited first, 21 of 21)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://mlsanity.com/paper/1606.06031/) (2016)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [Expert Gate: Lifelong Learning with a Network of Experts](https://mlsanity.com/paper/1611.06194/) (2016)
- [OLMoE: Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2409.02060/) (2024)
- [BinaryBERT: Pushing the Limit of BERT Quantization](https://mlsanity.com/paper/2012.15701/) (2020)
- [BiLLM: Pushing the Limit of Post-Training Quantization for LLMs](https://mlsanity.com/paper/2402.04291/) (2024)
- [Distributed Gaussian Processes](https://mlsanity.com/paper/1502.02843/) (2015)
- [MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance](https://mlsanity.com/paper/2505.03804/) (2025)
- [GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance](https://mlsanity.com/paper/2505.07004/) (2025)
- [STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs](https://mlsanity.com/paper/2408.01803/) (2024)
- [QUARK: Quantization-Enabled Circuit Sharing for Transformer Acceleration by Exploiting Common Patterns in Nonlinear Operations](https://mlsanity.com/paper/2511.06767/) (2025)
- [SpecQuant: Spectral Decomposition and Adaptive Truncation for Ultra-Low-Bit LLMs Quantization](https://mlsanity.com/paper/2511.11663/) (2025)
- [KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models](https://mlsanity.com/paper/2602.11184/) (2026)

## Built on by (most cited first, 2 of 2)

- [Beyond Independent Optimization: Compression, MoE Routing, and Quantization Interactions in Multimodal Edge Intelligence](https://mlsanity.com/paper/2607.20981/) (2026)
- [Pricing the Risk of Runtime Compression: Anytime-Valid Admission and a Served-Output Law for Compressed Serving State](https://mlsanity.com/paper/2608.15810/) (2026)

## Abstract (arXiv)

Mixture-of-Experts (MoE) based large language models (LLMs) offer strong performance but suffer from high memory and computation costs. Weight binarization provides extreme efficiency, yet existing binary methods designed for dense LLMs struggle with MoE-specific issues, including cross-expert redundancy, task-agnostic importance estimation, and quantization-induced routing shifts. To this end, we propose MoBiE, the first binarization framework tailored for MoE-based LLMs. MoBiE is built on three core innovations: 1. using joint SVD decomposition to reduce cross-expert redundancy; 2. integrating global loss gradients into local Hessian metrics to enhance weight importance estimation; 3. introducing an error constraint guided by the input null space to mitigate routing distortion. Notably, MoBiE achieves these optimizations while incurring no additional storage overhead, striking a balance between efficiency and model performance. Extensive experiments demonstrate that MoBiE consistently outperforms state-of-the-art binary methods across multiple MoE-based LLMs and benchmarks. For example, on Qwen3-30B-A3B, MoBiE reduces perplexity by 52.2%, improves average zero-shot performance by 43.4%, achieves over 2 × inference speedup, and further shortens quantization time. The code is available at https://github.com/Kishon-zzx/MoBiE.