tensorblock/MBZUAI-Paris_Atlas-Chat-9B-GGUF
Quantization vs MBZUAI-Paris/Atlas-Chat-9B. tensorblock/MBZUAI-Paris_Atlas-Chat-9B-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 169 tensors match exactly and 295 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/169, MLP 0/126, Attention 0/168