ggml-org/Ministral-3-3B-Instruct-2512-GGUF
Quantization (fewer layers) vs mistralai/Ministral-3-3B-Instruct-2512-BF16. ggml-org/Ministral-3-3B-Instruct-2512-GGUF matches part of mistralai/Ministral-3-3B-Instruct-2512-BF16 (236 of its 458 tensors; the rest of mistralai/Ministral-3-3B-Instruct-2512-BF16 has no counterpart). On the shared part: ggml-org/Ministral-3-3B-Instruct-2512-GGUF is a GGUF quantization (Q8_0) of the same weights: 53 tensors match exactly and 183 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/53, MLP 0/78, Attention 0/104