mradermacher/Rocinante-XL-16B-v1-GGUF
Quantization vs TheDrummer/Rocinante-XL-16B-v1. mradermacher/Rocinante-XL-16B-v1-GGUF is a GGUF quantization (Q8_0) of the same weights: 109 tensors match exactly and 380 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/109, MLP 0/162, Attention 0/216