shisa-ai/shisa-v2-llama3.1-405b-GGUF
Quantization vs shisa-ai/shisa-v2-llama3.1-405b. shisa-ai/shisa-v2-llama3.1-405b-GGUF is a GGUF quantization (Q8_0) of the same weights: 237 tensors match exactly and 827 within quantization error.
Tensors changed: Embeddings 0/1, Attention 0/472, MLP 0/353, Norms 0/237, lm_head 0/1