mlx-community/deepseek-vl2-tiny-4bit

This model was converted to MLX format from prince-canuma/deepseek-vl2-tiny using mlx-vlm version 0.1.5. 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/deepseek-vl2-tiny-4bit --max-tokens 100 --temp 0.0
Downloads last month
101
Safetensors
Model size
646M params
Tensor type
FP16
·
U32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the HF Inference API does not support transformers models with pipeline type image-text-to-text

Collection including mlx-community/deepseek-vl2-tiny-4bit