tensorblock/SmolLM2-1.7B-GGUF
Quantization vs HuggingFaceTB/SmolLM2-1.7B. tensorblock/SmolLM2-1.7B-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 49 tensors match exactly and 169 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/96