mradermacher/frankencria-llama2-12.5b-v1.3-m.2-i1-GGUF
Quantization vs davzoku/frankencria-llama2-12.5b-v1.3-m.2. mradermacher/frankencria-llama2-12.5b-v1.3-m.2-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 121 tensors match exactly and 422 within quantization error.
Tensors changed: MLP 0/180, Norms 0/121, Attention 0/240, lm_head 0/1, Embeddings 0/1