mradermacher/gemma-3-4b-pt-i1-GGUF
Quantization (fewer layers) vs google/gemma-3-4b-pt. mradermacher/gemma-3-4b-pt-i1-GGUF matches part of google/gemma-3-4b-pt (443 of its 883 tensors; the rest of google/gemma-3-4b-pt has no counterpart). On the shared part: mradermacher/gemma-3-4b-pt-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 205 tensors match exactly and 238 within quantization error.
Tensors changed: Norms 0/205, MLP 0/102, Attention 0/136