preferedev/Roblox-Coder-v2_gguf
Full fine-tune vs unsloth/Qwen3.5-4B-GGUF. preferedev/Roblox-Coder-v2_gguf is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 0 of 0 layers.
Tensors changed: other 73/145, MLP 96/96, Norms 0/105, Attention 80/80