mradermacher/Ministral-3-14B-Instruct-2512-BF16-abliterated-i1-GGUF
Quantization (fewer layers) vs s3nh/Ministral-3-14B-Instruct-2512-BF16-abliterated. mradermacher/Ministral-3-14B-Instruct-2512-BF16-abliterated-i1-GGUF matches part of s3nh/Ministral-3-14B-Instruct-2512-BF16-abliterated (363 of its 585 tensors; the rest of s3nh/Ministral-3-14B-Instruct-2512-BF16-abliterated has no counterpart). On the shared part: mradermacher/Ministral-3-14B-Instruct-2512-BF16-abliterated-i1-GGUF is a GGUF quantization (IQ1_M) of the same weights: 81 tensors match exactly and 282 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160