mradermacher/granite-guardian-3.3-8b-GGUF

Same weights, converted vs ibm-granite/granite-guardian-3.3-8b. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160

On the Hub · Downloads on Model Pulse