Hob-forge/smeagle-4b
Quantization vs Qwen/Qwen3.5-4B-Base. Hob-forge/smeagle-4b is a GGUF quantization (Q8_0) of the same weights: 81 tensors match exactly and 129 within quantization error.
Tensors changed: Embeddings 0/1, MLP 0/96, Norms 0/81, Attention 0/32