tensorblock/Nous-Hermes-2-MoE-2x34B-GGUF
Quantization vs ibndias/Nous-Hermes-2-MoE-2x34B. tensorblock/Nous-Hermes-2-MoE-2x34B-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 181 tensors match exactly and 242 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/121, Attention 0/240, other 0/60