jkim96/granite-4.1-3b-DASHQ-Q2-GGUF
Quantization vs ibm-granite/granite-4.1-3b. jkim96/granite-4.1-3b-DASHQ-Q2-GGUF is a GGUF quantization (IQ2_XS) of the same weights: 81 tensors match exactly and 281 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160