mradermacher/GPT-OSS-26B-abliterated-Preview-GGUF
Quantization vs win10/GPT-OSS-26B-abliterated-Preview. mradermacher/GPT-OSS-26B-abliterated-Preview-GGUF is a GGUF quantization (Q8_0) of the same weights: 241 tensors match exactly and 122 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/61, MLP 0/60, Attention 0/240, lm_head 0/1