mradermacher/Apertus-70B-Instruct-2509-heretic-v2-i1-GGUF
Quantization vs surelio/Apertus-70B-Instruct-2509-heretic-v1.1.2. mradermacher/Apertus-70B-Instruct-2509-heretic-v2-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 321 tensors match exactly and 482 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/321, MLP 0/160, Attention 0/320