mlsanityData to 14 Oct 2026

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

arXiv 2402.17764 ↗First posted 27 Feb 2024cs.CL cs.LGcited by 308

Not on the map. Why?

Cited by 25 in Efficient LLM inference and serving, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recent research, such as BitNet, is paving the way for a new era of 1-bit Large Language Models (LLMs). In this work, we introduce a 1-bit LLM variant, namely BitNet b1.58, in which every single parameter (or weight) of the LLM is ternary {-1, 0, 1}. It matches the full-precision (i.e., FP16 or BF16) Transformer LLM with the same model size and training tokens in terms of both perplexity and end-task performance, while being significantly more cost-effective in terms of latency, memory, throughput, and energy consumption. More profoundly, the 1.58-bit LLM defines a new scaling law and recipe for training new generations of LLMs that are both high-performance and cost-effective. Furthermore, it enables a new computation paradigm and opens the door for designing specific hardware optimized for 1-bit LLMs.

Key facts. Cited by 308 papers in the map (data through 14 Oct 2026). Builds on 21 of its 28 references that are in the map. First posted on arXiv 27 Feb 2024.

Builds on

21 of 28 references.

References · 21

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  5. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  6. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  7. 2016Pointer Sentinel Mixture Modelscited by 3,096
  8. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,883
  9. 2019BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questionscited by 2,183
  10. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,164
  11. 2020GLU Variants Improve Transformercited by 1,804
  12. 2019Root Mean Square Layer Normalizationcited by 1,480
9 more
  1. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
  2. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,298
  3. 2016The LAMBADA dataset: Word prediction requiring a broad discourse contextcited by 992
  4. 2017Crowdsourcing Multiple Choice Science Questionscited by 765
  5. 2023QuIP: 2-Bit Quantization of Large Language Models With Guaranteescited by 414
  6. 2024QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebookscited by 378
  7. 2023BitNet: Scaling 1-bit Transformers for Large Language Modelscited by 189
  8. 2019Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answeringcited by 59
  9. 2021PokeBNN: A Binary Pursuit of Lightweight Accuracycited by 49

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 107; 2025: 107; 2026: 94.

308 papers.

Sort:

By area:

  1. 2024Llumnix: Dynamic Scheduling for Large Language Model Servingcited by 174
  2. 2024SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Modelscited by 170
  3. 2024EfficientQAT: Efficient Quantization-Aware Training for Large Language Modelscited by 127
  4. 2024On-Device Language Models: A Comprehensive Reviewcited by 104
  5. 2024Scaling Laws for Precisioncited by 95
  6. 2024A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challengescited by 90
  7. 2024SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Accelerationcited by 72
  8. 2024PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compressioncited by 61
  9. 2024Compressing Large Language Models using Low Rank and Low Precision Decompositioncited by 59
  10. 2024VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Modelscited by 57
  11. 2025Optimizing Large Language Model Training Using FP4 Quantizationcited by 56
  12. 2024Training-Free Activation Sparsity in Large Language Modelscited by 55
38 more
  1. 2025MiniCPM4: Ultra-Efficient LLMs on End Devicescited by 52
  2. 2024Training of Physical Neural Networkscited by 49
  3. 2025ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantizationcited by 46
  4. 2025BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulationcited by 43
  5. 2025BitNet b1.58 2B4T Technical Reportcited by 38
  6. 2024BitsFusion: 1.99 bits Weight Quantization of Diffusion Modelcited by 37
  7. 2025Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical Reasoningcited by 37
  8. 2024SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanismscited by 31
  9. 2024LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scalecited by 31
  10. 20241.58-bit FLUXcited by 31
  11. 2024The Future of Large Language Model Pre-training is Federatedcited by 30
  12. 2024Fast Matrix Multiplications for Lookup Table-Quantized LLMscited by 29
  13. 2024u-μP: The Unit-Scaled Maximal Update Parametrizationcited by 29
  14. 2024VIAssist: Adapting Multi-modal Large Language Models for Users with Visual Impairmentscited by 25
  15. 2024Recurrent neural networks: vanishing and exploding gradients are not the end of the storycited by 25
  16. 2024Scalable MatMul-free Language Modelingcited by 25
  17. 2024Q-Sparse: All Large Language Models can be Fully Sparsely-Activatedcited by 25
  18. 2024CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge Collaborationcited by 25
  19. 2024LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Gridcited by 22
  20. 2024ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Modelscited by 22
  21. 2024The Complexity Dynamics of Grokkingcited by 22
  22. 2025QuEST: Stable Training of LLMs with 1-Bit Weights and Activationscited by 22
  23. 2025Bitnet.cpp: Efficient Edge Inference for Ternary LLMscited by 22
  24. 2024Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scalecited by 21
  25. 2024Effective Interplay between Sparsity and Quantization: From Theory to Practicecited by 19
  26. 2024Progressive Mixed-Precision Decoding for Efficient LLM Inferencecited by 18
  27. 2024Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokenscited by 18
  28. 2025DarwinLM: Evolutionary Structured Pruning of Large Language Modelscited by 18
  29. 2025BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMscited by 18
  30. 2025Tool Unlearning for Tool-Augmented LLMscited by 17
  31. 2025Scaling Law for Quantization-Aware Trainingcited by 17
  32. 2024BitNet a4.8: 4-bit Activations for 1-bit LLMscited by 16
  33. 2024Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devicescited by 15
  34. 2024ESPACE: Dimensionality Reduction of Activations for Model Compressioncited by 15
  35. 2024MeanCache: User-Centric Semantic Caching for LLM Web Servicescited by 14
  36. 2024Optimal Quantization for Matrix Multiplicationcited by 14
  37. 2025Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Modelscited by 13
  38. 2024Blessing or curse? A survey on the Impact of Generative AI on Fake Newscited by 12

50 most cited of 308 All 308 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024OneBit: Towards Extremely Low-bit Large Language Models
  2. 2024New Solutions on LLM Acceleration, Optimization, and Application
  3. 2024When are 1.58 bits enough? A Bottom-up Exploration of BitNet Quantization
  4. 2025A Systematic Evaluation of On-Device LLMs: Quantization, Performance, and Resources
  5. 2026ScaleBITS: Scalable Bitwidth Search for Hardware-Aligned Mixed-Precision LLMs
  6. 2025Systematic Characterization of LLM Quantization: A Performance, Energy, and Quality Perspective
  7. 2024BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration
  8. 2024I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models