mradermacher/OpenChat-3.5-0106_BlockExpansion-48Layers-End-GGUF
Quantization vs Pretergeek/OpenChat-3.5-0106_10.7B_48Layers-Appended. mradermacher/OpenChat-3.5-0106_BlockExpansion-48Layers-End-GGUF is a GGUF quantization (Q8_0) of the same weights: 97 tensors match exactly and 338 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/97, MLP 0/144, Attention 0/192