DavidAU/Qwen3.6-40B-Finetune-Z1-Thinking

IMPORTANT:

This is a light tune only ; for production usage it requires a more extensive tune to add new knowledge/skills.

Qwen3.6-40B-Finetune-Z1-Thinking

Expanded Qwen 3.6 27B to 40B parameters [from 64 to 96 layers] via modified Mergekit.

Fine tune via Unsloth on local hardware to finalize expansion.

Prep stage for advanced, in depth tuning.

Prep stage for Heretic/Uncensored builds too.

AKA "3.6" prep for version of this model:

https://huggingface.co/DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking

[180 likes+, 13k+ source downloads. 50k+ quants downloaded.]

[ more to come]