mudler/Qwopus-MoE-35B-A3B-APEX-GGUF
Quantization vs samuelcardillo/Qwopus-MoE-35B-A3B-GGUF. mudler/Qwopus-MoE-35B-A3B-APEX-GGUF is a GGUF quantization (F16) of the same weights: 261 tensors match exactly and 432 within quantization error.
Tensors changed: lm_head 0/1, Norms 0/131, other 0/181, Attention 0/100, MLP 0/280