bartowski/Qwen2.5-72B-0.6x-Instruct-GGUF
Quantization vs ddh0/Qwen2.5-72B-0.6x-Instruct. bartowski/Qwen2.5-72B-0.6x-Instruct-GGUF is a GGUF quantization (Q8_0) of the same weights: 401 tensors match exactly and 562 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/161, MLP 0/240, Attention 0/560