mlx-community/UI-TARS-7B-SFT-4bit

This model was converted to MLX format from bytedance-research/UI-TARS-7B-SFT using mlx-vlm version 0.1.14. 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 mlx-community/UI-TARS-7B-SFT-4bit --max-tokens 100 --temp 0.0 --prompt "Describe this image." --image <path_to_image>
Downloads last month
20
Safetensors
Model size
1.87B params
Tensor type
FP16
·
U32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Collection including mlx-community/UI-TARS-7B-SFT-4bit