LFQ (LLM quantization): current frontier — recent, not yet superseded in the knowledge base. 0 paper(s) critique it, 0 beat it on benchmarks — not ranked as a superseded baseline.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 GPTQ. Newer alternatives in the same sub-problem include QVGGT, LFQ, ADMM-Q, OSAQ, SEPTQ.

LLM quantization

LFQ

LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs

On the frontierfirst seen May 28, 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Current frontier — recent, not yet superseded in the knowledge base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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.

QVGGTQVGGT: Post-Training Quantized Visual Geometry Grounded Transformer
May 29, 2026
LFQLFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs
May 28, 2026
ADMM-QADMM-Q: An Improved Hessian-based Weight Quantizer for Post-Training Quantization of Large Language Models
May 11, 2026
OSAQOSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization
May 6, 2026
SEPTQSEPTQ: A Simple and Effective Post-Training Quantization Paradigm for Large Language Models
Apr 11, 2026
QMCQMC: Efficient SLM Edge Inference via Outlier-Aware Quantization and Emergent Memories Co-Design
Jan 21, 2026
Grouped Lattice Vector Quantization (GLVQ)Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compression
Oct 23, 2025
LUQLUQ: Layerwise Ultra-Low Bit Quantization for Multimodal Large Language Models
Sep 28, 2025
Bi-VLMBi-VLM: Pushing Ultra-Low Precision Post-Training Quantization Boundaries in Vision-Language Models
Sep 23, 2025
Fair-GPTQFair-GPTQ: Bias-Aware Quantization for Large Language Models
Sep 18, 2025