PiehSoft/Qwen3.6-40B-Deckard-MTP

Quantization vs DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF. PiehSoft/Qwen3.6-40B-Deckard-MTP is a GGUF quantization (Q6_K) of the same weights: 673 tensors match exactly and 602 within quantization error.

Tensors changed: lm_head 0/1, Norms 0/313, other 0/433, Attention 0/240, MLP 0/288

On the Hub · Downloads on Model Pulse