bartowski/cerebras_GLM-4.5-Air-REAP-82B-A12B-GGUF Text Generation • 85B • Updated 6 days ago • 9.09k • 17
Cerebras REAP Collection Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 11 items • Updated 2 days ago • 28
REAP the Experts: Why Pruning Prevails for One-Shot MoE compression Paper • 2510.13999 • Published 13 days ago • 4