mradermacher/G9v3-3B-i1-GGUF
Quantization vs ai9stars/G9v3-3B. mradermacher/G9v3-3B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 105 tensors match exactly and 366 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 0/156, Attention 0/208, Norms 0/105