mradermacher/Ministral-3-3B-Instruct-2512-Heresy-Unfiltered-GGUF
Same weights, converted (fewer layers) vs imbleach/Ministral-3-3B-Instruct-2512-Heresy-Unfiltered. mradermacher/Ministral-3-3B-Instruct-2512-Heresy-Unfiltered-GGUF matches part of imbleach/Ministral-3-3B-Instruct-2512-Heresy-Unfiltered (236 of its 458 tensors; the rest of imbleach/Ministral-3-3B-Instruct-2512-Heresy-Unfiltered has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/53, MLP 0/78, Attention 0/104