cdtio33/Ornith-1.5-397B-IQ2_XXS-DFlash-Drafter-GGUF
Full fine-tune vs z-lab/Qwen3.5-397B-A17B-DFlash. cdtio33/Ornith-1.5-397B-IQ2_XXS-DFlash-Drafter-GGUF is a GGUF (Q4) of different weights. Fine-tune: 100% of the weights changed, across 6 of 6 layers.
Tensors changed: Norms 25/25, Attention 24/24