wici-ai/inferssd · AI Repo StatsWIwici-ai/inferssd
Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
Inference & local LLMC++ Apache-2.0 77created 2026-10-22 #apple-silicon#cuda#gguf#inference#llama-cpp#llm#metal#mixture-of-experts#ssd