🦆 zecanard/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-2bit-affine

This model was converted to MLX from DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking using mlx-vlm version 0.4.4. Please refer to the original model card for more details.

🌟 Quality

Quantized vision language model with 3.153 bits per weight.

mlx_vlm.convert --quantize --q-bits 2 --q-group-size 32 --q-mode affine

🛠️ Customizations

This quant is aware of the current date, and also enables thinking (if available). You may disable this behavior by deleting the following line from the chat template:

{%- set enable_thinking = true %}

🖥️ Use with mlx

pip install -U mlx-vlm

mlx_vlm.generate --model zecanard/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-2bit-affine --max-tokens 100 --temperature 0 --prompt "Describe this image." --image <path_to_image>