Disya/gemma-4-12B-it-qat-q4_0-unquantized-heretic-gguf

Same weights, converted vs coder3101/gemma-4-12B-it-qat-q4_0-unquantized-heretic. Same weights stored in another dtype (BF16 → BF16/F32), plus 49 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/184

On the Hub · Downloads on Model Pulse