mradermacher/GRAG-HERMES-MOBIUS-R1-LLAMA-i1-GGUF
Quantization vs avemio-digital/German-RAG-HERMES-MOBIUS-R1-LLAMA. mradermacher/GRAG-HERMES-MOBIUS-R1-LLAMA-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 65 tensors match exactly and 226 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128