MLX Community · First MLX build 1 May 2026
Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-4.5bit-msq
MLX
TextVision apache-2.0
A 40B parameter vision and text model, with one MLX build at 5-bit.
- Parameters
- 40B From Hugging Face
- Quantisation
- 5-bit Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-4.5bit-msq
- Memory needed
- 10 GB Estimate, unified memory
- Download
- 6.5 GB Weights, estimated
- Downloads
- 68 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 10 GB at 5-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-vlm$ pip install -U mlx-vlm
$ python -m mlx_vlm.generate --model mlx-community/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-4.5bit-msq --image photo.jpg --prompt "Describe this image"MLX builds
1 on mlx-community| Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-4.5bit-msq | 5-bit | 6.5 GB | 10 GB | 68 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.