mradermacher/Hunyuan-A13B-Instruct-i1-GGUF
Quantization vs tencent/Hunyuan-A13B-Instruct. mradermacher/Hunyuan-A13B-Instruct-i1-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 161 tensors match exactly and 225 within quantization error.
Tensors changed: MLP 0/128, Embeddings 0/1, Attention 0/128, Norms 0/129