DevQuasar/ibm-granite.granite-4.0-h-small-GGUF

Same weights, converted vs ibm-granite/granite-4.0-h-small. Same weights stored in another dtype (BF16 → F16/F32), plus 196 new tensors.

Tensors changed: Embeddings 0/1, other 0/80, Norms 0/81, MLP 0/40, Attention 0/16

On the Hub · Downloads on Model Pulse