sandeshrajx/

gpt-oss-20b-reap-0.5-gguf

gpt-oss-20b-reap-0.50-q8_0.gguf was generate by using convert_hf_to_gguf.py script in llama.cpp repo with a bf16 version of the model as source.

Hence the size is bigger compared to a mxfp4 q8 gguf file like in https://huggingface.co/sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf