mradermacher/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF
Quantization vs adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML. mradermacher/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF is a GGUF quantization (Q8_0) of the same weights: 193 tensors match exactly and 98 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/48, Attention 0/192, lm_head 0/1