# TernaryLLM: Ternarized Large Language Model

arXiv: https://arxiv.org/abs/2406.07177 · HTML: https://mlsanity.com/paper/2406.07177/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 34 references that are in the map.
- First posted on arXiv 11 Jun 2024.

## Builds on (most cited first, 23 of 23)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [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)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models](https://mlsanity.com/paper/2308.13137/) (2023)
- [QuIP: 2-Bit Quantization of Large Language Models With Guarantees](https://mlsanity.com/paper/2307.13304/) (2023)
- [LLM-QAT: Data-Free Quantization Aware Training for Large Language Models](https://mlsanity.com/paper/2305.17888/) (2023)
- [Ternary Weight Networks](https://mlsanity.com/paper/1605.04711/) (2016)
- [Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models](https://mlsanity.com/paper/2209.13325/) (2022)
- [PB-LLM: Partially Binarized Large Language Models](https://mlsanity.com/paper/2310.00034/) (2023)
- [DB-LLM: Accurate Dual-Binarization for Efficient LLMs](https://mlsanity.com/paper/2402.11960/) (2024)
- [Exploring the Limits of Transfer Learning with Unified Model in the Cybersecurity Domain](https://mlsanity.com/paper/2302.10346/) (2023)

## Built on by (most cited first, 17 of 17)

- [ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization](https://mlsanity.com/paper/2502.02631/) (2025)
- [PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization](https://mlsanity.com/paper/2410.05265/) (2024)
- [INT-FlashAttention: Enabling Flash Attention for INT8 Quantization](https://mlsanity.com/paper/2409.16997/) (2024)
- [Tequila: Trapping-free Ternary Quantization for Large Language Models](https://mlsanity.com/paper/2509.23809/) (2025)
- [TerEffic: Highly Efficient Ternary LLM Inference on FPGA](https://mlsanity.com/paper/2502.16473/) (2025)
- [AngelSlim: A more accessible, comprehensive, and efficient toolkit for large model compression](https://mlsanity.com/paper/2602.21233/) (2026)
- [GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling](https://mlsanity.com/paper/2604.18556/) (2026)
- [CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs](https://mlsanity.com/paper/2606.26650/) (2026)
- [Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization](https://mlsanity.com/paper/2608.01078/) (2026)
- [PT2-LLM: Post-Training Ternarization for Large Language Models](https://mlsanity.com/paper/2510.03267/) (2025)
- [Scaling Laws For Mixed Quantization](https://mlsanity.com/paper/2410.06722/) (2024)
- [EntroLLM: Entropy Encoded Weight Compression for Efficient Large Language Model Inference on Edge Devices](https://mlsanity.com/paper/2505.02380/) (2025)
- [Towards Understanding Best Practices for Quantization of Vision-Language Models](https://mlsanity.com/paper/2601.15287/) (2026)
- [Hardware Generation and Exploration of Lookup Table-Based Accelerators for 1.58-bit LLM Inference](https://mlsanity.com/paper/2604.25183/) (2026)
- [Vanishing Contributions: A Unified Framework for Smooth and Iterative Model Compression](https://mlsanity.com/paper/2510.09696/) (2025)
- [R2Q: Towards Robust 2-Bit Large Language Models via Residual Refinement Quantization](https://mlsanity.com/paper/2511.21736/) (2025)
- [HESTIA: A Hessian-Guided Differentiable Quantization-Aware Training Framework for Extremely Low-Bit LLMs](https://mlsanity.com/paper/2601.20745/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have achieved remarkable performance on Natural Language Processing (NLP) tasks, but they are hindered by high computational costs and memory requirements. Ternarization, an extreme form of quantization, offers a solution by reducing memory usage and enabling energy-efficient floating-point additions. However, applying ternarization to LLMs faces challenges stemming from outliers in both weights and activations. In this work, observing asymmetric outliers and non-zero means in weights, we introduce Dual Learnable Ternarization (DLT), which enables both scales and shifts to be learnable. We also propose Outlier-Friendly Feature Knowledge Distillation (OFF) to recover the information lost in extremely low-bit quantization. The proposed OFF can incorporate semantic information and is insensitive to outliers. At the core of OFF is maximizing the mutual information between features in ternarized and floating-point models using cosine similarity. Extensive experiments demonstrate that our TernaryLLM surpasses previous low-bit quantization methods on the standard text generation and zero-shot benchmarks for different LLM families. Specifically, for one of the most powerful open-source models, LLaMA-3, our approach (W1.58A16) outperforms the previous state-of-the-art method (W2A16) by 5.8 in terms of perplexity on C4 and by 8.2% in terms of average accuracy on zero-shot tasks.