SicariusSicariiStuff/Fiendish_LLAMA_3B_GGUF
Quantization vs SicariusSicariiStuff/Fiendish_LLAMA_3B. SicariusSicariiStuff/Fiendish_LLAMA_3B_GGUF is a GGUF quantization (Q8_0) of the same weights: 57 tensors match exactly and 198 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112