twinkle-ai/gemma-3-4B-T1-it-GGUF
Same weights, converted vs twinkle-ai/gemma-3-4B-T1-it. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136, lm_head 0/1
Same weights, converted vs twinkle-ai/gemma-3-4B-T1-it. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136, lm_head 0/1