heath0xFF author hub
DeepSeek V4 Flash 0731 REAP K160 GGUF GGUF quantizations of 0xSero/DeepSeek V4 Flash 0731 REAP https://huggingface.co/0xSero/DeepSeek V4 Flash 0731 REAP — a REAP expert pruned DeepSeek V4 Flash checkpoint retaining 160 of 256 routed experts per MoE layer. IMPORTANT For llama.cpp…
Models
2
Downloads
3,008
Run models locally with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.