mradermacher/OpenMedResearch-Gemma-4E4N-i1-GGUF
Quantization (fewer layers) vs EpistemeAI/OpenMedResearch-Gemma-4E4N. mradermacher/OpenMedResearch-Gemma-4E4N-i1-GGUF matches part of EpistemeAI/OpenMedResearch-Gemma-4E4N (677 of its 2130 tensors; the rest of EpistemeAI/OpenMedResearch-Gemma-4E4N has no counterpart). On the shared part: mradermacher/OpenMedResearch-Gemma-4E4N-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