ShayonSarker/SmolLM3-3B-Q4_K_M-GGUF
Quantization vs HuggingFaceTB/SmolLM3-3B-Base. ShayonSarker/SmolLM3-3B-Q4_K_M-GGUF is a GGUF quantization (Q8_0) of the same weights: 73 tensors match exactly and 253 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/144