mradermacher/Samantha-qwen-0.5b-ptbr-i1-GGUF
Quantization vs Guilherme34/Samantha-qwen-0.5b-ptbr. mradermacher/Samantha-qwen-0.5b-ptbr-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 121 tensors match exactly and 169 within quantization error.
Tensors changed: Embeddings 0/1, MLP 0/72, Attention 0/168, Norms 0/49