philtheriver/Qwen3.6-27B-ROCmFPX
Full fine-tune vs unsloth/Qwen3.6-27B-MTP-GGUF. philtheriver/Qwen3.6-27B-ROCmFPX is a GGUF (Q8_0_ROCMFPX) of different weights. Fine-tune: 100% of the weights changed, across 0 of 0 layers.
Tensors changed: other 1/145, Norms 0/216