bartowski/allura-org_Q3-30b-A3b-Pentiment-GGUF

Same weights, converted vs allura-org/Q3-30b-A3b-Pentiment. Same weights stored in another dtype (BF16 → BF16/F32), plus 144 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/193, MLP 0/48, Attention 0/192

On the Hub · Downloads on Model Pulse