gghfez/gpt-oss-20b-SOMbliterated-mxfp4
Quantization vs kabachuha/gpt-oss-20b-SOMbliterated. gghfez/gpt-oss-20b-SOMbliterated-mxfp4 is a GGUF quantization (MXFP4/Q8_0) of the same weights: 193 tensors match exactly and 98 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/49, MLP 0/48, Attention 0/192