mradermacher/gemma-4-E2B-home-assistant-i1-GGUF
Quantization (fewer layers) vs mewse/gemma-4-E2B-home-assistant. mradermacher/gemma-4-E2B-home-assistant-i1-GGUF matches part of mewse/gemma-4-E2B-home-assistant (505 of its 1951 tensors; the rest of mewse/gemma-4-E2B-home-assistant has no counterpart). On the shared part: mradermacher/gemma-4-E2B-home-assistant-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 228 tensors match exactly and 277 within quantization error.
Tensors changed: Embeddings 0/2, Norms 0/227, MLP 0/105, other 0/71, Attention 0/100