mradermacher/Gemma-3-Gaia-PT-BR-4b-it-GGUF
Same weights, converted (fewer layers) vs CEIA-UFG/Gemma-3-Gaia-PT-BR-4b-it. mradermacher/Gemma-3-Gaia-PT-BR-4b-it-GGUF matches part of CEIA-UFG/Gemma-3-Gaia-PT-BR-4b-it (444 of its 883 tensors; the rest of CEIA-UFG/Gemma-3-Gaia-PT-BR-4b-it has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136