$\text{Log}_\text{b}$Quant: Quantizing Language Models in Logarithmic Space
Quantization has become an invaluable tool to reduce memory requirements and inference speed of modern language models, in particular to make them available for consumer setups and edge devices. While previous work has primarily focused on uniform quantization codebooks, such approaches are prone to suboptimal representations due to low-frequency high-magnitude weights. We introduce Log$_\text{b}$Quant, a novel logarithmic quantization approach with adjustable bases, to adapt to common parameter distributions. We show that our method exhibits superior performance at 4-bit precision on several
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownQuantBench →
- LinkedLinked via unknownQuantization →
- LinkedLinked via unknownquant-kit →
- PossiblePossibly related (embedding) · 35%bitsandbytes-foundation/bitsandbytes →
“Possibly related via embedding similarity 0.68 (not asserted). Timestamp check: artifact after paper (+6d).”
- LinkedLinked via arxiv author · 85%Jeremias Bohn →
“$\text{Log}_\text{b}$Quant: Quantizing Language Models in Logarithmic Space”
- LinkedLinked via arxiv author · 85%Tizian Dippold →
“$\text{Log}_\text{b}$Quant: Quantizing Language Models in Logarithmic Space”
- LinkedLinked via arxiv author · 85%Mahdi Koubaa →
“$\text{Log}_\text{b}$Quant: Quantizing Language Models in Logarithmic Space”
- LinkedLinked via arxiv author · 85%Elias R. Wahl →
“$\text{Log}_\text{b}$Quant: Quantizing Language Models in Logarithmic Space”