bartowski/google_gemma-3-1b-it-qat-GGUF
Same weights, converted vs google/gemma-3-1b-it-qat-q4_0-unquantized. Same weights stored in another dtype (BF16 → BF16/F32).
Tensors changed: Embeddings 0/1, Norms 0/157, MLP 0/78, Attention 0/104
Same weights, converted vs google/gemma-3-1b-it-qat-q4_0-unquantized. Same weights stored in another dtype (BF16 → BF16/F32).
Tensors changed: Embeddings 0/1, Norms 0/157, MLP 0/78, Attention 0/104