bartowski/ibm-granite_granite-4.1-8b-GGUF
Same weights, converted vs ibm-granite/granite-4.1-8b. Same weights stored in another dtype (BF16 → BF16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160
Same weights, converted vs ibm-granite/granite-4.1-8b. Same weights stored in another dtype (BF16 → BF16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160