erlidev/Qwen3.8-27B-DSpark-GGUF
Full fine-tune vs RadixArk/Qwen3.8-27B-DSpark. erlidev/Qwen3.8-27B-DSpark-GGUF is a GGUF (BF16) of different weights. Fine-tune: 100% of the weights changed, across 0 of 0 layers.
Tensors changed: other 3/3, Norms 21/21, Attention 10/10