Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

ACM Turing Celebration Conference - China (ACM TURC)

QuantaBit: Quantum-Assisted Mixed-Precision LLM Quantization and Inference

Yuchen Li, Gongwei Li, Zihang Fang, Juncheng Jia, Jian Tang, Zhiguo Huang, J. Z. Han, Ruochen Liu

Published Jul 11, 2026• 0 citations
Publisher

Abstract

QuantaBit integrates a quantum-enhanced quantization solver with a mixed-precision inference engine. Starting from a pretrained FP16 Large Language Model (LLM), it analyzes layer-wise sensitivity, constructs a Hamiltonian that combines quantization-induced accuracy loss with compression loss, maps candidate bitwidths to compact binary variables, and finally solves the resulting QUBO on a Coherent Ising Machine (CIM). The decoded mixed-precision bitwidth allocation is then used to perform mixed quantization. QuantaBit invokes the inference engine for bitwidth-aware packing, heterogeneous kernel dispatch, and PagedAttention-based KV-cache management. Experiments on four LLMs show that QuantaBit decreases perplexity over uniform W4 and Cplex under the same average-bitwidth target, while deployed models reduce weight memory by over 3.4x, improve throughput by 15%, and extend context length by 53%.

DOI
10.1145/3833142.3833162

Related papers

Q4Q: Quantum for Quantization in Large Language Models

Gongwei Li, Yuchen Li, Juncheng Jia +2 more

Mixed-precision quantization, which dynamically allocates bitwidths across layers, poses an NP-hard combinatorial optimization problem, since the exponentially growing search space makes traditional heuristic or sampling-based methods difficult to scale and prone to suboptimal solutions. Recent advances in quantum computing open up a promising new avenue, as its intrinsic parallelism enables efficient exploration of large combinatorial spaces and offers the potential to overcome the limitations of classical search. We propose Q4Q (Quantum-computing for Quantization), a quantum-based method for efficient bitwidth allocation in model quantization. Q4Q formulates accuracy loss and compression overhead as Hamiltonians, allowing Pareto-optimal solutions to be obtained from a single sampling. Guided by layer sensitivity, the method adapts bitwidth allocation to balance accuracy and compression. Experiments on several 7B models show that Q4Q achieves a 3–8 orders of magnitude speedup over traditional machine learning, improves Pareto solution quality by 3–15%, and significantly enhances energy efficiency. This work offers a new paradigm for lightweight deployment of large models in edge scenarios and underscores the promise of quantum computing in combinatorial optimization.

IEEE International Conference on Acoustics Speech and Signal Processing•Apr 21, 2026•1 citation

Quantum-enhanced Large Language Models on Quantum Hardware via Cayley Unitary Adapters

Borja Aizpurua, Sukhbinder Singh, Augustine Kshetrimayum +2 more

Large language models (LLMs) have transformed artificial intelligence, yet classical architectures impose a fundamental constraint: every trainable parameter demands classical memory that scales unfavourably with model size. Quantum computing offers a qualitatively different pathway, but practical demonstrations on real hardware have remained elusive for models of practical relevance. Here we show that Cayley-parameterised unitary adapters -- quantum circuit blocks inserted into the frozen projection layers of pre-trained LLMs and executed on a 156-qubit IBM Quantum System Two superconducting processor -- improve the perplexity of Llama 3.1 8B, an 8-billion-parameter model in widespread use, by 1.4% with only 6,000 additional parameters and end-to-end inference validated on real Quantum Processing Unit (QPU). A systematic study on SmolLM2 (135M parameters), chosen for its tractability, reveals monotonically improving perplexity with unitary block dimension, 83% recovery of compression-induced degradation, and correct answers to questions that both classical baselines fail -- with a sharp noise-expressivity phase transition identifying the concrete path to quantum utility at larger qubit scales.

quant-pharXiv:2605.05914•May 8, 2026•0 citations

Practical Quantum CIM Empowerment via All-Domestic-Core Agentic Large Model

Rui Wang, Lu Diannan

Quantum computing devices are recognized as powerful tools for solving NP-complete problems. How-ever, the intricacy of their modeling presents notable barriers for non-specialists, while the tedious iteration of constraint weights and modeling methodologies also consumes substantial effort on the part of experts. To address these challenges, this study integrates a femtosecond laser-pumped Coherent Ising Machine (CIM) with an LLM-driven agentic system by leveraging the LangGraph and LangChain frameworks. Com-prehensive investigations demonstrate that large language models (LLMs) can effectively perform such tasks in modeling as QUBO/Ising model calibration, constraint weight decision iteration and rapid validation of literature-reported schemes. Notably, all these tasks can be fully implemented based on domestic large models, combined with domestically developed CIM hardware, we truly achieve the practical empowerment of quantum CIM that fully relies on all-domestic agentic large models and hardware. This work successfully realizes robust technological integration, laying a solid foundation for subsequent research. Nevertheless, it also identifies the persisting challenges in the two cutting-edge fields of large models and quantum computing at the current stage. Encouragingly, we unexpectedly discover a promising new paradigm where accumulated knowledge from agent-assisted quantum computing iterations reciprocally enhances the agent’s own problem-solving capability, thereby addressing these challenges.

•Apr 27, 2026•0 citations

Practical Quantum CIM Empowerment via All-Domestic-Core Agentic Large Model

Wang Rui, Lu Diannan

Quantum computing devices are recognized as powerful tools for solving NP-complete problems. However, the intricacy of their modeling presents notable barriers for non-specialists, while the tedious iteration of constraint weights and modeling methodologies also consumes substantial effort on the part of experts. To address these challenges, this study integrates a femtosecond laser-pumped Coherent Ising Machine (CIM) with an LLM-driven agentic system by leveraging the LangGraph and LangChain frameworks. Comprehensive investigations demonstrate that large language models (LLMs) can effectively perform such tasks in modeling as QUBO/Ising model calibration, constraint weight decision iteration and rapid validation of literature-reported schemes. Notably, all these tasks can be fully implemented based on domestic large models, combined with domestically developed CIM hardware, we truly achieve the practical empowerment of quantum CIM that fully relies on all-domestic agentic large models and hardware. This work successfully realizes robust technological integration, laying a solid foundation for subsequent research. Nevertheless, it also identifies the persisting challenges in the two cutting-edge fields of large models and quantum computing at the current stage. Encouragingly, we unexpectedly discover a promising new paradigm where accumulated knowledge from agent-assisted quantum computing iterations reciprocally enhances the agent's own problem-solving capability, thereby addressing these challenges.

cs.AICross-listedarXiv:2605.23934•Apr 27, 2026•0 citations

QuLoC: Photonic Quantum-Assisted Low-Rank LLM Compression

Xiao-Hui Ni, Yu-Han Yao, Yu-Ze Zhu +4 more

As LLMs grow in size, compression becomes increasingly important for efficient deployment. SVD-based low-rank compression reduces parameter counts but can degrade downstream performance. To improve performance after compression, we introduce QuLoC, a photonic quantum-assisted LLM compression algorithm that uses quantum circuit outputs to gate the retained low-rank components during training. Model performance is recovered through local functional reconstruction followed by end-to-end knowledge distillation. After training, the gating coefficients are absorbed into the low-rank factors, allowing the compressed model to run on classical hardware without executing quantum circuits during inference. Experiments on Qwen3.5-4B show that QuLoC achieves a 9.73\% relative improvement in average accuracy over state-of-the-art baselines across multiple downstream tasks, demonstrating its effectiveness. We further evaluate QuLoC on LLaMA-7B at different parameter compression ratios. It achieves comparable or higher average downstream accuracy than state-of-the-art baselines, supporting its applicability to a larger model across different compression settings. These results motivate further exploration of photonic quantum-assisted compression for larger models and more complex agentic tasks.

quant-pharXiv:2609.40146•Oct 1, 2026•0 citations

CompactifAI: Extreme Compression of Large Language Models using Quantum-Inspired Tensor Networks

Saeed S. Jahromi, Uygar Kurt, Sukhi Singh +3 more

Large Language Models (LLMs) like ChatGPT and LlaMA offer immense opportunities but face challenges due to their vast size, leading to high training/inference costs and energy demands.Traditional compression methods focus on reducing neurons or precision.We introduce CompactifAI, a novel LLM compression using quantum-inspired Tensor Networks to compress the model's correlation space.Testing on LlaMA-2 7B showed a 93% memory and 70% parameter reduction, with minimal accuracy loss (2-3%) and significant training (50%) and inference (25%) speedups.

European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)•Jan 1, 2025•0 citations
QuantaBit integrates a quantum-enhanced quantization solver with a mixed-precision inference engine. Starting from a pretrained FP16 Large Language Model (LLM), it analyzes layer-wise sensitivity, constructs a Hamiltonian that combines quantization-induced accuracy loss with compression loss, maps candidate bitwidths to compact binary variables, and finally solves the resulting QUBO on a Coherent Ising Machine (CIM). The decoded mixed-precision bitwidth allocation is then used to perform mixed quantization. QuantaBit invokes the inference engine for bitwidth-aware packing, heterogeneous kernel dispatch, and PagedAttention-based KV-cache management. Experiments on four LLMs show that QuantaBit decreases perplexity over uniform W4 and Cplex under the same average-bitwidth target, while deployed models reduce weight memory by over 3.4x, improve throughput by 15%, and extend context length by 53%.
Mixed-precision quantization, which dynamically allocates bitwidths across layers, poses an NP-hard combinatorial optimization problem, since the exponentially growing search space makes traditional heuristic or sampling-based methods difficult to scale and prone to suboptimal solutions. Recent advances in quantum computing open up a promising new avenue, as its intrinsic parallelism enables efficient exploration of large combinatorial spaces and offers the potential to overcome the limitations of classical search. We propose Q4Q (Quantum-computing for Quantization), a quantum-based method for efficient bitwidth allocation in model quantization. Q4Q formulates accuracy loss and compression overhead as Hamiltonians, allowing Pareto-optimal solutions to be obtained from a single sampling. Guided by layer sensitivity, the method adapts bitwidth allocation to balance accuracy and compression. Experiments on several 7B models show that Q4Q achieves a 3–8 orders of magnitude speedup over traditional machine learning, improves Pareto solution quality by 3–15%, and significantly enhances energy efficiency. This work offers a new paradigm for lightweight deployment of large models in edge scenarios and underscores the promise of quantum computing in combinatorial optimization.
Large language models (LLMs) have transformed artificial intelligence, yet classical architectures impose a fundamental constraint: every trainable parameter demands classical memory that scales unfavourably with model size. Quantum computing offers a qualitatively different pathway, but practical demonstrations on real hardware have remained elusive for models of practical relevance. Here we show that Cayley-parameterised unitary adapters -- quantum circuit blocks inserted into the frozen projection layers of pre-trained LLMs and executed on a 156-qubit IBM Quantum System Two superconducting processor -- improve the perplexity of Llama 3.1 8B, an 8-billion-parameter model in widespread use, by 1.4% with only 6,000 additional parameters and end-to-end inference validated on real Quantum Processing Unit (QPU). A systematic study on SmolLM2 (135M parameters), chosen for its tractability, reveals monotonically improving perplexity with unitary block dimension, 83% recovery of compression-induced degradation, and correct answers to questions that both classical baselines fail -- with a sharp noise-expressivity phase transition identifying the concrete path to quantum utility at larger qubit scales.
Quantum computing devices are recognized as powerful tools for solving NP-complete problems. How-ever, the intricacy of their modeling presents notable barriers for non-specialists, while the tedious iteration of constraint weights and modeling methodologies also consumes substantial effort on the part of experts. To address these challenges, this study integrates a femtosecond laser-pumped Coherent Ising Machine (CIM) with an LLM-driven agentic system by leveraging the LangGraph and LangChain frameworks. Com-prehensive investigations demonstrate that large language models (LLMs) can effectively perform such tasks in modeling as QUBO/Ising model calibration, constraint weight decision iteration and rapid validation of literature-reported schemes. Notably, all these tasks can be fully implemented based on domestic large models, combined with domestically developed CIM hardware, we truly achieve the practical empowerment of quantum CIM that fully relies on all-domestic agentic large models and hardware. This work successfully realizes robust technological integration, laying a solid foundation for subsequent research. Nevertheless, it also identifies the persisting challenges in the two cutting-edge fields of large models and quantum computing at the current stage. Encouragingly, we unexpectedly discover a promising new paradigm where accumulated knowledge from agent-assisted quantum computing iterations reciprocally enhances the agent’s own problem-solving capability, thereby addressing these challenges.
Quantum computing devices are recognized as powerful tools for solving NP-complete problems. However, the intricacy of their modeling presents notable barriers for non-specialists, while the tedious iteration of constraint weights and modeling methodologies also consumes substantial effort on the part of experts. To address these challenges, this study integrates a femtosecond laser-pumped Coherent Ising Machine (CIM) with an LLM-driven agentic system by leveraging the LangGraph and LangChain frameworks. Comprehensive investigations demonstrate that large language models (LLMs) can effectively perform such tasks in modeling as QUBO/Ising model calibration, constraint weight decision iteration and rapid validation of literature-reported schemes. Notably, all these tasks can be fully implemented based on domestic large models, combined with domestically developed CIM hardware, we truly achieve the practical empowerment of quantum CIM that fully relies on all-domestic agentic large models and hardware. This work successfully realizes robust technological integration, laying a solid foundation for subsequent research. Nevertheless, it also identifies the persisting challenges in the two cutting-edge fields of large models and quantum computing at the current stage. Encouragingly, we unexpectedly discover a promising new paradigm where accumulated knowledge from agent-assisted quantum computing iterations reciprocally enhances the agent's own problem-solving capability, thereby addressing these challenges.
As LLMs grow in size, compression becomes increasingly important for efficient deployment. SVD-based low-rank compression reduces parameter counts but can degrade downstream performance. To improve performance after compression, we introduce QuLoC, a photonic quantum-assisted LLM compression algorithm that uses quantum circuit outputs to gate the retained low-rank components during training. Model performance is recovered through local functional reconstruction followed by end-to-end knowledge distillation. After training, the gating coefficients are absorbed into the low-rank factors, allowing the compressed model to run on classical hardware without executing quantum circuits during inference. Experiments on Qwen3.5-4B show that QuLoC achieves a 9.73\% relative improvement in average accuracy over state-of-the-art baselines across multiple downstream tasks, demonstrating its effectiveness. We further evaluate QuLoC on LLaMA-7B at different parameter compression ratios. It achieves comparable or higher average downstream accuracy than state-of-the-art baselines, supporting its applicability to a larger model across different compression settings. These results motivate further exploration of photonic quantum-assisted compression for larger models and more complex agentic tasks.
Large Language Models (LLMs) like ChatGPT and LlaMA offer immense opportunities but face challenges due to their vast size, leading to high training/inference costs and energy demands.Traditional compression methods focus on reducing neurons or precision.We introduce CompactifAI, a novel LLM compression using quantum-inspired Tensor Networks to compress the model's correlation space.Testing on LlaMA-2 7B showed a 93% memory and 70% parameter reduction, with minimal accuracy loss (2-3%) and significant training (50%) and inference (25%) speedups.