OsirisPtah-Coder-v5-GGUF

GGUF quantized version of OsirisPtah-Coder-v5 (Qwen2.5-Coder-7B-Instruct, abliterated). For use with llama.cpp on Apple Silicon.

Files

File	Description
OsirisPtah-Coder-v5-Q6_K.gguf	GGUF quantized model

Usage with llama.cpp

./llama-server -m <model-file>.gguf -ngl 99