mradermacher/Awqward2.5-32B-Instruct-i1-GGUF
Quantization vs maldv/Awqward2.5-32B-Instruct. mradermacher/Awqward2.5-32B-Instruct-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 321 tensors match exactly and 450 within quantization error.
Tensors changed: Norms 0/129, MLP 0/192, Attention 0/448, Embeddings 0/1, lm_head 0/1