sleepyeldrazi author hub
DeepSeek V4 Flash — REAP K128 Uniform REAP pruned DeepSeek V4 Flash at K128 128 routed experts per MoE layer . Prunes 50% of routed experts via Cerebras REAP Router weighted Expert Activation Pruning , preserving all attention, embeddings, shared experts, router, and MTP compone…
Models
2
Downloads
0
Run models locally with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.