ArtusDev/allura-org_Gemma-3-Glitter-4B-GGUF
Quantization (fewer layers) vs allura-org/Gemma-3-Glitter-4B. ArtusDev/allura-org_Gemma-3-Glitter-4B-GGUF matches part of allura-org/Gemma-3-Glitter-4B (444 of its 883 tensors; the rest of allura-org/Gemma-3-Glitter-4B has no counterpart). On the shared part: ArtusDev/allura-org_Gemma-3-Glitter-4B-GGUF is a GGUF quantization (Q8_0) of the same weights: 205 tensors match exactly and 239 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136