tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF
Quantization vs Qwen/Qwen1.5-MoE-A2.7B-Chat. tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 145 tensors match exactly and 170 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/96, Attention 0/168, lm_head 0/1