SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF
Quantization vs timteh673/Qwen3.5-122B-A10B-Opus-Reasoning-GGUF. SixVolts/Qwen3.5-122B-A10B-Opus-Reasoning-MTP-GGUF is a GGUF quantization (Q3_K_XL) of the same weights: 313 tensors match exactly and 518 within quantization error.
Tensors changed: lm_head 0/1, other 0/217, Norms 0/157, Attention 0/120, MLP 0/336