Superseded baseline#33 of 80 most-superseded
AMQ
AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language ModelsLLM quantization · first seen Sep 15, 2025
superseded — cited as a baseline and beaten by newer methods
1 papers critique it · 1 beat it on benchmarks
What papers say
Verbatim critique sentences, each from a paper that cites AMQ as a baseline.
“it remains relatively slow for large-scale models”
— SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs
Beaten on benchmarks
Head-to-head results where a newer method reports beating AMQ. Values are copied from the source paper's tables — verify against the cited paper.
- SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs
SignRoundV2 beats AMQ · Avg [Llama3.1-8B, Avg Bits 2.5]
68.57 vs 58.65
- SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs
SignRoundV2 beats AMQ · Avg [Qwen3-8B, Avg Bits 2.5]
66.82 vs 58.62
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.