Cerebras REAP
Collection
Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 30 items • Updated • 137
Facu Vlad J
groxaxo
AI & ML interests
Cloud Engineer · AI Automation Engineer · Quantization Gremlin
I build cloud systems, automate the boring parts, and squeeze absurd efficiency out of AI models. Into infra, agents, vLLM, local GPU rigs, and quantizations that make big models run where they probably shouldn’t.
Recent Activity
new activity about 3 hours ago
groxaxo/Qwen3.6-27B-GPTQ-Pro-4bit:Modify the configuration file updated a model about 6 hours ago
groxaxo/Qwen3.6-27B-GPTQ-Pro-4bit liked a model about 6 hours ago
groxaxo/Qwen3.6-27B-GPTQ-Pro-4bitOrganizations
None yet