Mungert/Pantheon-Proto-RP-1.8-30B-A3B-GGUF
Partial fine-tune vs Qwen/Qwen3-30B-A3B-Base. Mungert/Pantheon-Proto-RP-1.8-30B-A3B-GGUF is a GGUF (Q8_0) of different weights. Partial change: 80% of the weights changed (attention, lm_head, mlp, norms), in 48 of 48 layers.
Tensors changed: Embeddings 0/1, Norms 107/193, MLP 48/48, Attention 192/192, lm_head 1/1