SUPEROXIDES/GOETIA_V1.3_ABSOLUTE_HERETIC_ARA_26B-A4B_-_GGUF_-_MXFP4_MOE

Same weights, converted vs Naphula/Goetia-26B-A4B-v1.3-Absolute-Heretic-ARA. Same weights stored in another dtype (BF16 → F16/F32), plus 151 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/271, MLP 0/90, other 0/30, Attention 0/115

On the Hub · Downloads on Model Pulse