MemSFT-Qwen3-OpenSWI-Memory-8B-GGUF

A GGUF-quantized 8B model distributed by mradermacher on Hugging Face, derived from the Qwen3-8B base with apparent supervised fine-tuning oriented toward memory-related behavior (MemSFT/OpenSWI/Memory naming). Packaged for efficient local inference via llama.cpp-compatible runtimes. Source: supabase.