SicariusSicariiStuff/Impish_QWEN_14B-1M_GGUF_HA
Quantization vs SicariusSicariiStuff/Impish_QWEN_14B-1M. SicariusSicariiStuff/Impish_QWEN_14B-1M_GGUF_HA is a GGUF quantization (Q2_HA) of the same weights: 241 tensors match exactly and 338 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/97, MLP 0/144, Attention 0/336, lm_head 0/1