PMQ (Mixture-of-experts routing): superseded — cited as a baseline and beaten by newer methods. 1 paper(s) critique it, 3 beat it on benchmarks — #54 of 1370 most-superseded. Sub-problem: cluster led by MoEQuant. Newer alternatives in the same sub-problem include BitsMoE, GEMQ, KBVQ-MoE, MC# (Mixture-Compressor-sharp).

Mixture-of-experts routing

PMQ

Superseded baseline#54 of 1,370 most-superseded

Superseded — cited as a baseline and beaten by newer methods

1 papers critique it · 3 beat it on benchmarks

What papers say

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

existing approaches remain constrained to local, layer-wise bit allocation and thus fail to capture variations in expert importance across layers

— GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs

Beaten on benchmarks

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

GEMQ beats PMQ
16.20 vs 20.77
C4 perplexity · [Mixtral-8x7B at 1.5 bpe]
GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs
QESC beats PMQ
65.03 vs 61.35
0-shot^8 · [Phi3.5-moe, 2.06 bits]
EAC-MoE: Expert-Selection Aware Compressor for Mixture-of-Experts Large Language Models

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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.