tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v5-GGUF
Quantization vs tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v5. tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v5-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 290 tensors match exactly and 328 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/184