pugant/Qwen3.8-27B-MTP-Q4_0_ROCMFP4_STRIX_LEAN
Quantization vs Qwen/Qwen3.8-27B. pugant/Qwen3.8-27B-MTP-Q4_0_ROCMFP4_STRIX_LEAN is a GGUF quantization (Q4_0_ROCMFP4_STRIX_LEAN) of the same weights: 161 tensors match exactly and 1 within quantization error.
Tensors changed: Norms 0/161, Embeddings 0/1