mradermacher/GPT-OSS-30B-Preview-GGUF
Quantization vs win10/GPT-OSS-30B-Preview. mradermacher/GPT-OSS-30B-Preview-GGUF is a GGUF quantization (Q8_0) of the same weights: 289 tensors match exactly and 146 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/73, MLP 0/72, Attention 0/288