Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit
mlx-community/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit
Text generation · mlx
8-bit Open on Hugging Face
Parameters
39B
Weights (est.)
≈ 41.5 GB
Mac memory (est.)
64 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit --prompt "Hello"
Details
- Base model
- DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking (quantized)
- Vendor
- DavidAU
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 6.1K in the last 30 days · 96K all time · 58 likes
- Published
- 2026-05-02 · updated 2026-05-03 (6mo ago)
- Languages
- en, zh
- Tags
- qwen3_5, unsloth, fine tune, heretic, uncensored, abliterated, multi-stage tuned., all use cases, coder, creative, creative writing, fiction writing