ngquocvinh/YuE2-3B-GGUF
Quantization vs m-a-p/YuE2-3B. ngquocvinh/YuE2-3B-GGUF is a GGUF quantization (Q8_0_F16) of the same weights: 342 tensors match exactly and 280 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/225, MLP 0/172, Attention 0/224