hugobugo34/Qwen3.8-27B-ROCmFPX-GGUF
Quantization vs Qwen/Qwen3.8-27B. hugobugo34/Qwen3.8-27B-ROCmFPX-GGUF is a GGUF quantization (T100/Q6_K) of the same weights: 161 tensors match exactly and 1 within quantization error.
Tensors changed: Norms 0/161, Embeddings 0/1