Vakamalla-Anitha/granite-4.1-3b-oracle-nl2sql-gguf
Quantization vs ibm-granite/granite-4.1-3b. Vakamalla-Anitha/granite-4.1-3b-oracle-nl2sql-gguf is a GGUF quantization (Q4_K_M) 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