mradermacher/Yi-Coder-9B-Chat-Instruct-TIES-MoE-v1.0-GGUF
Quantization vs BenevolenceMessiah/Yi-Coder-9B-Chat-Instruct-TIES-MoE-v1.0. mradermacher/Yi-Coder-9B-Chat-Instruct-TIES-MoE-v1.0-GGUF is a GGUF quantization (Q8_0) of the same weights: 145 tensors match exactly and 194 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/97, Attention 0/192, lm_head 0/1, other 0/48