mradermacher/Safiron-i1-GGUF
Quantization vs Safiron/Safiron. mradermacher/Safiron-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 73 tensors match exactly and 254 within quantization error.
Tensors changed: MLP 0/108, Attention 0/144, Norms 0/73, Embeddings 0/1, lm_head 0/1