mradermacher/Huihui-Mistral-Small-3.2-24B-Instruct-2506-abliterated-llamacppfixed-GGUF
Quantization (fewer layers) vs nicoboss/Huihui-Mistral-Small-3.2-24B-Instruct-2506-abliterated-llamacppfixed. mradermacher/Huihui-Mistral-Small-3.2-24B-Instruct-2506-abliterated-llamacppfixed-GGUF matches part of nicoboss/Huihui-Mistral-Small-3.2-24B-Instruct-2506-abliterated-llamacppfixed (363 of its 585 tensors; the rest of nicoboss/Huihui-Mistral-Small-3.2-24B-Instruct-2506-abliterated-llamacppfixed has no counterpart). On the shared part: mradermacher/Huihui-Mistral-Small-3.2-24B-Instruct-2506-abliterated-llamacppfixed-GGUF is a GGUF quantization (Q8_0) of the same weights: 81 tensors match exactly and 282 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160, lm_head 0/1