RTN (LLM quantization): superseded — cited as a baseline and beaten by newer methods. 2 paper(s) critique it, 10 beat it on benchmarks — #6 of 80 most-superseded. Sub-problem: cluster led by RTN. Newer alternatives in the same sub-problem include STaR-Quant, Timestep-Aware SVDQuant-GPTQ, BWLA, Bit-by-Bit, Benford-Quant.

Superseded baseline#6 of 80 most-superseded

RTN

LLM quantization

superseded — cited as a baseline and beaten by newer methods

2 papers critique it · 10 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites RTN as a baseline.

“the quantization error increases significantly when the number of bits is small, especially when significant outliers exist.”
— CCQ: Convolutional Code for Extreme Low-bit Quantization in LLMs
“uniform grids spend disproportionate capacity on rare large magnitudes while under-resolving dense near-zero regions; the mismatch is exacerbated in layers whose weight magnitudes span multiple decades.”
— Benford's Law as a Distributional Prior for Post-Training Quantization of Large Language Models

Beaten on benchmarks

Head-to-head results where a newer method reports beating RTN. Values are copied from the source paper's tables — verify against the cited paper.

STaR-Quant beats RTN · Avg. [W4A4 (4-bit weight and activation) on LLADA-8B]
57.07 vs 44.23
STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models
STaR-Quant beats RTN · Avg. [W4A4 (4-bit weight and activation) on LLADA-1.5-8B]
66.93 vs 53.12
STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models
STaR-Quant beats RTN · Avg. [W4A4 (4-bit weight and activation) on DREAM-7B]
63.59 vs 49.53
STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models
ApiQ beats RTN · WikiText2 PPL [LLaMA-2-7B, 3-bit]
5.77 vs 6.66
Enhancing Ultra-Low-Bit Quantization of Large Language Models Through Saliency-Aware Partial Retraining
ApiQ beats RTN · C4 PPL [LLaMA-2-7B, 3-bit]
7.48 vs 8.40
Enhancing Ultra-Low-Bit Quantization of Large Language Models Through Saliency-Aware Partial Retraining
ApiQ beats RTN · WikiText2 PPL
5.12 vs 5.51
Enhancing Ultra-Low-Bit Quantization of Large Language Models Through Saliency-Aware Partial Retraining
ApiQ beats RTN · C4 PPL
6.83 vs 7.18
Enhancing Ultra-Low-Bit Quantization of Large Language Models Through Saliency-Aware Partial Retraining
Benford-Quant beats RTN · Perplexity [3 bits, Small models]
70.87 vs 755.19
Benford's Law as a Distributional Prior for Post-Training Quantization of Large Language Models
Benford-Quant beats RTN · Perplexity [4 bits, Small models]
32.28 vs 38.91
Benford's Law as a Distributional Prior for Post-Training Quantization of Large Language Models
Benford-Quant beats RTN · Perplexity [4 bits, Large models]
7.02 vs 17.22
Benford's Law as a Distributional Prior for Post-Training Quantization of Large Language Models
Reasoning-QAT beats RTN · Avg. [Qwen3-0.6B W3G128]
31.67 vs 5.07
What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study
Reasoning-QAT beats RTN · Avg. [R1-Qwen-1.5B W3G128]
43.26 vs 10.08
What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study

Newer alternatives

Recent methods in the same sub-problem, not yet superseded in the knowledge base.