trubisky/Qwen3.5-2B-RCOL
Quantization vs Qwen/Qwen3.5-2B. trubisky/Qwen3.5-2B-RCOL is a GGUF quantization (IQ3_XXS/IQ3_S) of the same weights: 61 tensors match exactly and 97 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/61, MLP 0/72, Attention 0/24