mlx-community

/

Qwen2.5-VL-32B-Instruct-bf16

like 5

Follow

MLX Community 5k

When running this model, the response is simply to repeat "!!!!!!!!!!!!!!......".
The 8 bit quantization version of this model works well.
LM studio version:0.3.14 b5
MLX version info:

• mlx-engine==765f4a6
• mlx==0.24.0
• mlx-lm==0.22.2
• mlx-vlm==0.1.21