Is Reasoning-QAT superseded?

Reasoning-QAT (LLM quantization): current frontier — recent, not yet superseded in the knowledge base. 0 paper(s) critique it, 0 beat it on benchmarks — not ranked as a superseded baseline. Sub-problem: cluster led by SmoothQuant. Newer alternatives in the same sub-problem include OffQ, FAIR-Calib, InfoQuant, ConQuR, Activation Residual Hessian Quantization (ARHQ).

LLM quantization

Reasoning-QAT

What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study

On the frontierfirst seen Jan 21, 2026

Current frontier — recent, not yet superseded in the knowledge base

0 papers critique it · 0 beat it on benchmarks

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.

OffQOffQ: Taming Structured Outliers in LLM Quantization by Offsetting
Jun 5, 2026
FAIR-CalibFAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language Models
Jun 4, 2026
InfoQuantInfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization
May 25, 2026
ConQuRConQuR: Corner Aligned Activation Quantization via Optimized Rotations for LLMs
May 11, 2026
Activation Residual Hessian Quantization (ARHQ)Technical Report: Activation Residual Hessian Quantization (ARHQ) for Low-Bit LLM Quantization
Apr 30, 2026
LoRaQLoRaQ: Optimized Low Rank Approximation for 4-bit Quantization
Apr 20, 2026
OSCOSC: Hardware Efficient W4A4 Quantization via Outlier Separation in Channel Dimension
Apr 14, 2026
SliderQuantSliderQuant: Accurate Post-Training Quantization for LLMs
Mar 26, 2026
HeRo-QHeRo-Q: A General Framework for Stable Low Bit Quantization via Hessian Conditioning
Jan 29, 2026
Reasoning-QATWhat Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study
Jan 21, 2026
ConvRotConvRot: Rotation-Based Plug-and-Play 4-bit Quantization for Diffusion Transformers
Dec 3, 2025