DavidAU / Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF

Vision97.2K792Updated Sep 16, 2026

Downloads

97.2K

Likes

792

Last updated

Sep 16, 2026

License

apache-2.0

40 billion parameters (dense, not moe) expanded from 27B Qwen 3.6, then trained on Claude 4.6 Opus High Reasoning dataset via Unsloth on local hardware... but there is much more to the story - in comes DECKARD.

Tasks & library

  • image text to text

Tags

  • gguf
  • unsloth
  • fine tune
  • heretic
  • uncensored
  • abliterated

Technical specifications

ParametersNot available
LibraryNot available
Languagesen, zh
Licenseapache-2.0