Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method
-
cerebras/Qwen3-Coder-REAP-363B-A35B-FP8
Text Generation • 363B • Updated • 33 • 13 -
cerebras/Qwen3-Coder-REAP-246B-A35B-FP8
Text Generation • 246B • Updated • 107 • 17 -
cerebras/Qwen3-Coder-REAP-363B-A35B
Text Generation • 363B • Updated • 27 • 2 -
cerebras/Qwen3-Coder-REAP-246B-A35B
Text Generation • 246B • Updated • 30 • 4