kingjones777/Qwen3.8-27B-ROCmFPX-Q8_0-AGENT-GGUF
Quantization vs Qwen/Qwen3.8-27B. kingjones777/Qwen3.8-27B-ROCmFPX-Q8_0-AGENT-GGUF is a GGUF quantization (Q8_0_ROCMFPX_AGENT) of the same weights: 161 tensors match exactly and 151 within quantization error.
Tensors changed: Norms 0/161, MLP 0/101, Attention 0/48, Embeddings 0/1, lm_head 0/1