mradermacher/Gemma3-BanglaCoder-GGUF
Quantization (fewer layers) vs muzahid404/Gemma3-BanglaCoder. mradermacher/Gemma3-BanglaCoder-GGUF matches part of muzahid404/Gemma3-BanglaCoder (626 of its 1065 tensors; the rest of muzahid404/Gemma3-BanglaCoder has no counterpart). On the shared part: mradermacher/Gemma3-BanglaCoder-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