mradermacher/Calme-12B-Instruct-v0.1-GGUF
Quantization vs MaziyarPanahi/Calme-12B-Instruct-v0.1. mradermacher/Calme-12B-Instruct-v0.1-GGUF is a GGUF quantization (Q8_0) of the same weights: 113 tensors match exactly and 394 within quantization error.
Tensors changed: MLP 0/168, Norms 0/113, Attention 0/224, lm_head 0/1, Embeddings 0/1