dicksonhk/Qwen2.5-VL-3B-Instruct-AWQ-mlx-fp16
The Model dicksonhk/Qwen2.5-VL-3B-Instruct-AWQ-mlx-fp16 was converted to $MLX format from Qwen/Qwen2.5-VL-3B-Instruct-AWQ using $mlx-vlm version 0.1.15.
pip install -U mlx-vlm
python -m mlx_vlm.generate --model dicksonhk/Qwen2.5-VL-3B-Instruct-AWQ-mlx-fp16 --max-tokens 100 --temp 0.0 --prompt "Describe this image." --image <path_to_image>
- Downloads last month
- 24
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for dicksonhk/Qwen2.5-VL-3B-Instruct-AWQ-mlx-fp16
Base model
Qwen/Qwen2.5-VL-3B-Instruct
Quantized
Qwen/Qwen2.5-VL-3B-Instruct-AWQ