blascotobasco/L3.2-Ascendant-Prime-16E-A6B-GGUF

Same weights, converted vs blascotobasco/L3.2-Ascendant-Prime-16E-A6B. Same weights stored in another dtype (BF16 → F16/F32), plus 85 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/57, Attention 0/112, other 0/28

On the Hub · Downloads on Model Pulse