FadedRedStar/Ministral-3-8B-Reasoning-2512-heretic-GGUF
Quantization (fewer layers) vs coder3101/Ministral-3-8B-Reasoning-2512-heretic. FadedRedStar/Ministral-3-8B-Reasoning-2512-heretic-GGUF matches part of coder3101/Ministral-3-8B-Reasoning-2512-heretic (309 of its 531 tensors; the rest of coder3101/Ministral-3-8B-Reasoning-2512-heretic has no counterpart). On the shared part: FadedRedStar/Ministral-3-8B-Reasoning-2512-heretic-GGUF is a GGUF quantization (Q8_0) of the same weights: 69 tensors match exactly and 240 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/69, MLP 0/102, Attention 0/136