Cerebras REAP Collection Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 21 items • Updated 2 days ago • 80
Cerebras REAP Collection Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 21 items • Updated 2 days ago • 80
cerebras/DeepSeek-V3.2-REAP-508B-A37B Text Generation • 508B • Updated Dec 9, 2025 • 416 • 15
cerebras/DeepSeek-V3.2-REAP-345B-A37B Text Generation • 345B • Updated Dec 9, 2025 • 1.93k • 29
Cerebras REAP Collection Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 21 items • Updated 2 days ago • 80
cerebras/Kimi-Linear-REAP-35B-A3B-Instruct Text Generation • 35B • Updated Nov 6, 2025 • 920 • 59
cerebras/MiniMax-M2-REAP-172B-A10B Text Generation • 173B • Updated Nov 15, 2025 • 1.03k • 17
cerebras/DeepSeek-V3.2-REAP-508B-A37B Text Generation • 508B • Updated Dec 9, 2025 • 416 • 15
cerebras/DeepSeek-V3.2-REAP-345B-A37B Text Generation • 345B • Updated Dec 9, 2025 • 1.93k • 29