ITQ3_S: High-Fidelity 3-bit LLM Inference via Interleaved Ternary Quantization with Rotation-Domain Smoothing

ArXi:2603.27914v1 Announce Type: cross We present \textbf{ITQ3\_S} (Interleaved Ternary Quantization -- Specialized), a novel 3-bit weight quantization format for large language models (LLMs) that integrates \textbf{TurboQuant (TQ)}, a rotation-domain adaptive quantization strategy based on the Fast Walsh-Hadamard Transform (FWHT). Conventional 3-bit quantization methods suffer from catastrophic precision loss caused by heavy-tailed weight distributions and inter-channel outliers.