Alcoft/granite-3.1-3b-a800m-instruct-GGUF

Same weights, converted vs ibm-granite/granite-3.1-3b-a800m-instruct. Same weights stored in another dtype (BF16 → F16/F32), plus 64 new tensors.

Tensors changed: Embeddings 0/1, other 0/64, Norms 0/65, Attention 0/128

On the Hub · Downloads on Model Pulse