mradermacher/ELM-gpt-oss-20b-NSFW-v0.2-GGUF
Quantization vs EeeLM/ELM-gpt-oss-20b-NSFW-v0.2. mradermacher/ELM-gpt-oss-20b-NSFW-v0.2-GGUF is a GGUF quantization (Q8_0) of the same weights: 193 tensors match exactly and 98 within quantization error.
Tensors changed: Norms 0/49, MLP 0/48, Attention 0/192, lm_head 0/1, Embeddings 0/1