zecanard/Qwopus3.6-27B-v2-MLX-2bit-mixed_2_6

🦆 zecanard/Qwopus3.6-27B-v2-MLX-2bit-mixed26

This model was converted to MLX from `Jackrong/Qwopus3.6-27B-v2` using mlx-vlm version 0.6.3. Please refer to the original model card for more details.

🌟 Quality

Mixed-precision quantized vision language model with an effective 3.524 bits per weight. Combines the size and speed benefits of a 2-bit quant with higher precision where it matters most.

mlx_vlm.convert --quantize --q-group-size 32 --quant-predicate mixed_2_6

🛠️ 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, or changing true to false:

{%- set enable_thinking = true %}

A fix is also included for a thinking-related performance issue in Qwen 3.6.

🖥️ Use with mlx

pip install -U mlx-vlm

mlx_vlm.generate --model zecanard/Qwopus3.6-27B-v2-MLX-2bit-mixed_2_6 --max-tokens 100 --temperature 0 --prompt "Describe this image." --image <path_to_image>