mradermacher/Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-III-i1-GGUF
Quantization vs DavidAU/Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-III. mradermacher/Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-III-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 336 tensors match exactly and 270 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/269, MLP 0/67, Attention 0/268