mudler/Qwen-AgentWorld-35B-A3B-APEX-GGUF
Quantization vs Qwen/Qwen-AgentWorld-35B-A3B. mudler/Qwen-AgentWorld-35B-A3B-APEX-GGUF is a GGUF quantization (Q5_K/Q6_K) of the same weights: 141 tensors match exactly and 162 within quantization error.
Tensors changed: MLP 0/160, Attention 0/40, Norms 0/101, Embeddings 0/1, lm_head 0/1