mradermacher/Qwen-1_8B-i1-GGUF
Quantization vs Qwen/Qwen-1_8B. mradermacher/Qwen-1_8B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 73 tensors match exactly and 122 within quantization error.
Tensors changed: Attention 0/72, Norms 0/49, MLP 0/72, Embeddings 0/1, lm_head 0/1