mmnga/ArrowMint-Gemma3-4B-YUKI-v0.1-gguf
Quantization (fewer layers) vs DataPilot/ArrowMint-Gemma3-4B-YUKI-v0.1. mmnga/ArrowMint-Gemma3-4B-YUKI-v0.1-gguf matches part of DataPilot/ArrowMint-Gemma3-4B-YUKI-v0.1 (444 of its 883 tensors; the rest of DataPilot/ArrowMint-Gemma3-4B-YUKI-v0.1 has no counterpart). On the shared part: mmnga/ArrowMint-Gemma3-4B-YUKI-v0.1-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