vjchou/translategemma-4b-it-GGUF
Quantization (fewer layers) vs google/translategemma-4b-it. vjchou/translategemma-4b-it-GGUF matches part of google/translategemma-4b-it (444 of its 883 tensors; the rest of google/translategemma-4b-it has no counterpart). On the shared part: vjchou/translategemma-4b-it-GGUF is a GGUF quantization (Q4_K_M) 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