mradermacher/LibreGemma4e4b-i1-GGUF
Quantization (fewer layers) vs LibreYOLO/LibreGemma4e4b. mradermacher/LibreGemma4e4b-i1-GGUF matches part of LibreYOLO/LibreGemma4e4b (677 of its 2130 tensors; the rest of LibreYOLO/LibreGemma4e4b has no counterpart). On the shared part: mradermacher/LibreGemma4e4b-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 297 tensors match exactly and 380 within quantization error.
Tensors changed: Embeddings 0/2, Norms 0/296, MLP 0/126, other 0/85, Attention 0/168