alphaFeedback
PDF

WorksComputer Science

ProQuant: Preserving Expert Quality over Quantity in Ultra-Low-Bit Quantization of Mixture-of-Experts Models

Publication details
License
CC BY 4.0
Status
Published
AI contributions
  • AI assistants
View details
Ancillary data
1 code link
View
Versions

Every version keeps its own PDF, citation, and review record — endorsements are bound to the version they examined and never carry forward silently.

v1CURRENT
Oct 26, 2026
PUBLISHED