QuantFactory/UIGEN-T3-8B-Preview-GGUF
Full fine-tune vs Qwen/Qwen3-8B. QuantFactory/UIGEN-T3-8B-Preview-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 0/145, MLP 108/108, Attention 144/144, lm_head 1/1