mradermacher/granite-4.0-micro-heretic-GGUF

Same weights, converted vs DrRiceIO7/granite-4.0-micro-heretic. Same weights stored in another dtype (BF16 → F16/F32), plus 120 new tensors.

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

On the Hub · Downloads on Model Pulse