DavidAU · First MLX build 2 May 2026
Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking
MLX
Text apache-2.0
A 39B parameter text generation model from DavidAU, with one MLX build at 8-bit.
- Parameters
- 39B From Hugging Face
- Quantisation
- 8-bit Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit
- Memory needed
- 49 GB Estimate, unified memory
- Download
- 41.5 GB Weights, estimated
- Downloads
- 6.1K This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 49 GB at 8-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit --prompt "Hello"MLX builds
1 on mlx-community| Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit | 8-bit | 41.5 GB | 49 GB | 6.1K |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.