mmnga/cogito-v1-preview-qwen-32B-gguf
Quantization vs deepcogito/cogito-v1-preview-qwen-32B. mmnga/cogito-v1-preview-qwen-32B-gguf is a GGUF quantization (Q5_K_M) 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