Jul 2026
Reliability Scaling Laws for Quantized Large Language Models
This study reveals that while the performance scales monotonically with the total number of bits, the reliability scalings are nonlinear, indicating that quantizing moderately sized models offers the best reliability-efficiency trade-off.
Sirine Ayadi, S'andor Dar'oczi, Stephan Günnemann et al.
· Trans. Mach. Learn. Res. · 0 citations