mradermacher/Qwenwify2.5-32B-v4.6-ED-GGUF
Quantization vs Kaoeiri/Qwenwify2.5-32B-v4.6-ED. mradermacher/Qwenwify2.5-32B-v4.6-ED-GGUF is a GGUF quantization (Q8_0) of the same weights: 321 tensors match exactly and 450 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 0/448