mradermacher/Amadeus-Verbo-FI-Qwen2.5-14B-PT-BR-Instruct-GGUF
Quantization vs amadeusai/Amadeus-Verbo-FI-Qwen2.5-14B-PT-BR-Instruct. mradermacher/Amadeus-Verbo-FI-Qwen2.5-14B-PT-BR-Instruct-GGUF is a GGUF quantization (Q8_0) of the same weights: 241 tensors match exactly and 338 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/97, MLP 0/144, Attention 0/336, lm_head 0/1