{
 "tag": "llama.cpp",
 "kind": null,
 "product": null,
 "used_by": [],
 "parts": [],
 "notes": [
  {
   "handle": "sarg",
   "id": "fix-for-llama-cpp-cudamalloc-out-of-memory",
   "title": "Fix for llama.cpp cudaMalloc out of memory loading a 35GB Q8_0 MoE GGUF on a 48GB RTX PRO 5000",
   "status": "working"
  }
 ]
}