Mungert/Ministral-3-8B-Reasoning-2512-GGUF
Full fine-tune (fewer layers) vs mistralai/Ministral-3-8B-Base-2512. Mungert/Ministral-3-8B-Reasoning-2512-GGUF matches part of mistralai/Ministral-3-8B-Base-2512 (309 of its 531 tensors; the rest of mistralai/Ministral-3-8B-Base-2512 has no counterpart). On the shared part: Mungert/Ministral-3-8B-Reasoning-2512-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 34 of 34 layers.
Tensors changed: Embeddings 1/1, Norms 69/69, MLP 102/102, Attention 136/136, lm_head 1/1