KakoRel/Huihui-gemma-4-12B-coder-GGUF

Same weights, converted vs huihui-ai/Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated. Same weights stored in another dtype (F16/BF16 → F16/F32), plus 49 new tensors.

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

On the Hub · Downloads on Model Pulse