mradermacher/BigQwen2.5-52B-Instruct-i1-GGUF
Quantization vs mlabonne/BigQwen2.5-52B-Instruct. mradermacher/BigQwen2.5-52B-Instruct-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 521 tensors match exactly and 730 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/209, MLP 0/312, Attention 0/728