mradermacher/PopiT-Gemma-3-12B-Medical-SFT-1218-GGUF
Quantization (fewer layers) vs Hoshino-Yumetsuki/PopiT-Gemma-3-12B-Medical-SFT-1218. mradermacher/PopiT-Gemma-3-12B-Medical-SFT-1218-GGUF matches part of Hoshino-Yumetsuki/PopiT-Gemma-3-12B-Medical-SFT-1218 (626 of its 1065 tensors; the rest of Hoshino-Yumetsuki/PopiT-Gemma-3-12B-Medical-SFT-1218 has no counterpart). On the shared part: mradermacher/PopiT-Gemma-3-12B-Medical-SFT-1218-GGUF is a GGUF quantization (Q8_0) of the same weights: 289 tensors match exactly and 337 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/192