mlx-community
/

Qwen3.5-35B-A3B-4bit

Image-Text-to-Text

4-bit precision

Model card Files Files and versions

Resources

View closed (0)

disable thinking mode

#3 opened about 1 month ago by

Fantastic model. Getting 48 t/s on a 32GB M4 Mac Mini

#2 opened about 2 months ago by

Normalize tool-call format to JSON payload inside <tool_call>

#1 opened about 2 months ago by