mradermacher/Poro-34B-chat-OpenAssistant-GGUF
Quantization vs LumiOpen/Poro-34B-chat-OpenAssistant. mradermacher/Poro-34B-chat-OpenAssistant-GGUF is a GGUF quantization (Q8_0) of the same weights: 380 tensors match exactly and 163 within quantization error.
Tensors changed: Norms 0/218, MLP 0/216, Attention 0/108, Embeddings 0/1