Cerebras REAP
Collection
Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 30 items • Updated
• 122
Shihan Qu
zenmagnets
AI & ML interests
None yet
Recent Activity
new activity
1 day ago
lukealonso/MiniMax-M2.5-NVFP4:Here's the vLLM recipe I'm using with 2x RTX Pro 6000 liked
a model 3 days ago
nvidia/Qwen3.5-397B-A17B-NVFP4 new activity
3 days ago
Ex0bit/Kimi-K2.5-PRISM-REAP-530B-A32B:Anyone get this working on 4x RTX 6000 Pro? Organizations
None yet
upvoted a collection about 1 month ago