Abiray/Ministral-3-3B-Instruct-2512-Heresy-Unfiltered-GGUF
LoRA-style (fewer layers) vs MuXodious/Ministral-3-3B-Instruct-2512-absolute-heresy. Abiray/Ministral-3-3B-Instruct-2512-Heresy-Unfiltered-GGUF matches part of MuXodious/Ministral-3-3B-Instruct-2512-absolute-heresy (236 of its 458 tensors; the rest of MuXodious/Ministral-3-3B-Instruct-2512-absolute-heresy has no counterpart). On the shared part: Abiray/Ministral-3-3B-Instruct-2512-Heresy-Unfiltered-GGUF is a GGUF (FP16) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 26 of 26 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/53, MLP 78/78, Attention 104/104