mlx-community/deepseek-vl2-small-6bit

This model was converted to MLX format from prince-canuma/deepseek-vl2-small 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-small-6bit --max-tokens 100 --temp 0.0

Safetensors

Model size

3.65B params

Tensor type

FP16

U32

Inference Examples

Inference API (serverless) does not yet support transformers models for this pipeline type.