itzmealvin/MLX_Qwen2VL-2B-IT-Q8

This model was converted to MLX format from erax-ai/EraX-VL-2B-V1.5 using mlx-vlm version 0.1.23. Refer to the original model card for more details on the model.

Use with mlx

pip install -U mlx-vlm
python -m mlx_vlm.generate --model itzmealvin/MLX_Qwen2VL-2B-IT-Q8 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
Downloads last month
12
Safetensors
Model size
623M params
Tensor type
F16
·
U32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for itzmealvin/MLX_Qwen2VL-2B-IT-Q8

Base model

Qwen/Qwen2-VL-2B
Quantized
(4)
this model