prithivMLmods/gemma-4-12B-it-GGUF
Same weights, converted vs google/gemma-4-12B-it. Same weights stored in another dtype (BF16 → F16/F32), plus 49 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/184
Same weights, converted vs google/gemma-4-12B-it. Same weights stored in another dtype (BF16 → F16/F32), plus 49 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/184