bartowski/Gryphe_Pantheon-Proto-RP-1.8-30B-A3B-GGUF
Same weights, converted vs Gryphe/Pantheon-Proto-RP-1.8-30B-A3B. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 144 new tensors.
Tensors changed: MLP 0/48, Embeddings 0/1, Norms 0/193, Attention 0/192, lm_head 0/1