ccharnkij/Ministral-3-8B-Reasoning-2512-Uncensored-GGUF
LoRA-style (fewer layers) vs mistralai/Ministral-3-8B-Reasoning-2512. ccharnkij/Ministral-3-8B-Reasoning-2512-Uncensored-GGUF matches part of mistralai/Ministral-3-8B-Reasoning-2512 (309 of its 531 tensors; the rest of mistralai/Ministral-3-8B-Reasoning-2512 has no counterpart). On the shared part: ccharnkij/Ministral-3-8B-Reasoning-2512-Uncensored-GGUF is a GGUF (F16) 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 34 of 34 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/69, MLP 102/102, Attention 136/136, lm_head 0/1