SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights
Paper
•
2509.22944
•
Published
•
76
Celik
storianc
AI & ML interests
None yet
Recent Activity
liked
a model
8 days ago
huawei-csl/Qwen3-32B-4bit-SINQ
liked
a model
8 days ago
huawei-csl/Qwen3-14B-4bit-ASINQ
liked
a model
8 days ago
huawei-csl/Qwen3-14B-4bit-SINQ
Organizations
None yet
authored
a
paper
27 days ago